© 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. 36894
    Prev
    Next
    INDEX
    Explanations

    fragments related to technical information or discussions about software, programming, and troubleshooting

    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
    640
    +0.10
    0.7%
    311
    +0.09
    0.6%
    447
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.10
    0.27
    6
    +0.09
    0.18
    311
    +0.08
    -0.03
    Negative Logits
     accomp
    -0.46
    ona
    -0.43
     cele
    -0.43
    oult
    -0.43
    orescence
    -0.41
    ascript
    -0.41
     eq
    -0.41
     occupant
    -0.41
    heid
    -0.41
    roit
    -0.41
    POSITIVE LOGITS
     Wrong
    0.50
     Cookies
    0.47
     Subtle
    0.46
     Happ
    0.44
     Disapp
    0.42
     Aren
    0.41
     Ships
    0.41
    Wr
    0.41
    icably
    0.41
    DO
    0.40
    Activations Density 8.773%

    No Known Activations