© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12987
    Prev
    Next
    INDEX
    Explanations

    links to external URLs

    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
    766
    +0.09
    0.4%
    311
    +0.09
    0.4%
    459
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.09
    -0.00
    675
    +0.09
    0.14
    308
    +0.09
    0.10
    Negative Logits
     Galile
    -0.76
    tein
    -0.73
     removable
    -0.72
     Maiden
    -0.71
     Maid
    -0.70
     Sigma
    -0.70
     Machines
    -0.66
     Nig
    -0.66
     installations
    -0.65
    ļé
    -0.65
    POSITIVE LOGITS
    usat
    0.95
     charism
    0.93
    goo
    0.76
    amara
    0.73
     url
    0.71
    natureconservancy
    0.71
    iframe
    0.70
    json
    0.70
    Prev
    0.69
    www
    0.69
    Activations Density 6.837%

    No Known Activations