© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 8994
    Prev
    Next
    INDEX
    Explanations

    information related to various events, announcements, products, and services in a text, including movie premieres, digital environments, town events, documentary releases, game editions, community programs, digital currency, healthcare initiatives, and more

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    640
    +0.49
    2.2%
    167
    +0.15
    0.7%
    615
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.49
    0.44
    160
    +0.15
    0.25
    64
    +0.11
    -0.14
    Negative Logits
    oba
    -0.92
     outwe
    -0.89
    ophob
    -0.88
     inco
    -0.83
     diseng
    -0.81
     mistaken
    -0.80
     hasht
    -0.80
     equival
    -0.80
     irrit
    -0.80
    ophobia
    -0.80
    POSITIVE LOGITS
    Official
    1.08
    Shipping
    1.06
    NOTE
    1.06
    ccording
    1.03
     Specifications
    1.00
    Each
    0.98
    STER
    0.98
    Please
    0.96
    Quality
    0.96
    Custom
    0.95
    Activations Density 4.772%

    No Known Activations