© 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. 45722
    Prev
    Next
    INDEX
    Explanations

    details about people and their actions in various contexts

    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
    80
    +0.02
    0.6%
    435
    +0.02
    0.5%
    311
    +0.02
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.02
    0.13
    311
    +0.02
    -0.02
    393
    +0.02
    0.23
    Negative Logits
    ulhu
    -0.15
    aire
    -0.13
    imeter
    -0.13
    ionics
    -0.13
    ãĤ©
    -0.13
    iosis
    -0.12
     Clicker
    -0.12
    awaru
    -0.12
    ={
    -0.12
    uyomi
    -0.12
    POSITIVE LOGITS
    empty
    0.14
    dep
    0.12
    128
    0.11
    typ
    0.11
    sem
    0.11
    arser
    0.11
     noticeable
    0.11
    scale
    0.11
    inished
    0.11
     unpre
    0.11
    Activations Density 8.840%

    No Known Activations