© 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. 37179
    Prev
    Next
    INDEX
    Explanations

    discussions related to societal issues, moral dilemmas, and policy implications

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.20
    1.0%
    393
    +0.15
    0.7%
    498
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.33
    546
    +0.15
    0.19
    43
    +0.09
    0.17
    Negative Logits
    ety
    -0.64
    ield
    -0.62
    estate
    -0.62
    cell
    -0.57
     Medals
    -0.56
     unlocked
    -0.56
    ãĤĬ
    -0.55
    orthy
    -0.54
    orn
    -0.53
     Nex
    -0.52
    POSITIVE LOGITS
     uh
    0.99
     albeit
    0.91
     um
    0.90
     respectively
    0.78
     ah
    0.75
     namely
    0.75
     alas
    0.70
    wait
    0.69
     oh
    0.68
    =-=-
    0.66
    Activations Density 13.137%

    No Known Activations