© 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 Local
    9. 6-RES_SCL-AJT
    11. 36860
    Prev
    Next
    INDEX
    Explanations

    specific words or phrases that are capitalized and bolded in documents

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    276
    +0.14
    0.6%
    270
    +0.13
    0.6%
    195
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.14
    0.09
    208
    +0.13
    0.10
    501
    +0.13
    0.08
    Negative Logits
    ppo
    -0.83
    kaya
    -0.79
    kson
    -0.77
    ichick
    -0.77
    ategory
    -0.72
    chy
    -0.72
    IGHTS
    -0.72
    pload
    -0.67
    hee
    -0.66
    kers
    -0.66
    POSITIVE LOGITS
    angered
    1.11
    angering
    1.04
    urance
    1.03
    orph
    1.00
    owment
    0.94
    lich
    0.90
    ocrin
    0.89
    roit
    0.89
    ocrine
    0.87
    orse
    0.84
    Activations Density 9.019%

    No Known Activations