© 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. 31360
    Prev
    Next
    INDEX
    Explanations

    alternate words or spellings

    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
    503
    +0.12
    0.6%
    616
    +0.10
    0.5%
    626
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.12
    0.01
    503
    +0.10
    0.07
    85
    +0.09
    0.10
    Negative Logits
     guiActiveUnfocused
    -0.71
     conscience
    -0.62
     sliding
    -0.61
     spirits
    -0.58
     relaxation
    -0.57
     sentiments
    -0.56
     hearts
    -0.56
     Widow
    -0.55
     adrenaline
    -0.55
     Goods
    -0.55
    POSITIVE LOGITS
    ately
    1.36
    ently
    1.18
    acy
    1.15
    acies
    1.13
    encies
    1.13
    ency
    1.05
    uously
    1.04
    ably
    0.95
    antly
    0.93
    ially
    0.91
    Activations Density 8.828%

    No Known Activations