© 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. 2916
    Prev
    Next
    INDEX
    Explanations

    information related to movie descriptions and restaurant reviews

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    640
    +0.53
    2.0%
    549
    +0.13
    0.5%
    721
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.53
    0.31
    64
    +0.13
    -0.08
    6
    +0.12
    0.17
    Negative Logits
    ierrez
    -0.95
     risking
    -0.94
    soever
    -0.94
     Shinra
    -0.89
    imei
    -0.88
    atos
    -0.87
    utics
    -0.87
     blinded
    -0.86
    terday
    -0.86
    ername
    -0.84
    POSITIVE LOGITS
    âĵĺ
    1.11
    Buff
    1.11
    Trivia
    1.11
    Recommended
    1.11
    Newsletter
    1.08
    Score
    1.08
    âĸ¬
    1.07
    Advertisement
    1.06
    Reviewed
    1.06
    Bay
    1.06
    Activations Density 2.050%

    No Known Activations