© 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. 37181
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology and software development

    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
    373
    +0.11
    1.5%
    756
    +0.09
    1.3%
    459
    +0.07
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.11
    -0.19
    756
    +0.09
    -0.16
    138
    +0.07
    0.15
    Negative Logits
    reditary
    -0.23
    osate
    -0.22
     destro
    -0.19
     Amen
    -0.19
     exha
    -0.18
     mainland
    -0.17
     Citiz
    -0.17
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.17
     Forsaken
    -0.16
     Moonlight
    -0.16
    POSITIVE LOGITS
    \":
    0.18
    ibly
    0.17
    ited
    0.17
     understatement
    0.17
    raq
    0.16
    iator
    0.16
    itcher
    0.15
    itely
    0.15
    arted
    0.14
    itably
    0.14
    Activations Density 12.424%

    No Known Activations