© 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. 8905
    Prev
    Next
    INDEX
    Explanations

    text related to documentaries and films

    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
    274
    +0.15
    0.6%
    644
    +0.14
    0.5%
    336
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.13
    346
    +0.14
    0.07
    575
    +0.14
    0.08
    Negative Logits
    hare
    -1.06
    cffff
    -1.03
     Sabha
    -0.93
    pace
    -0.91
    aic
    -0.91
    places
    -0.86
    ymes
    -0.85
    usable
    -0.85
    ername
    -0.84
    words
    -0.80
    POSITIVE LOGITS
     filmmaker
    1.32
     filmmaking
    1.21
     filmmakers
    1.20
     documentary
    1.12
     film
    1.01
    ARY
    0.97
    arily
    0.94
     documentaries
    0.91
    Lens
    0.89
    HER
    0.88
    Activations Density 1.689%

    No Known Activations