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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36829
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts between different options or situations

    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
    322
    +0.06
    0.5%
    92
    +0.05
    0.4%
    689
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.06
    0.16
    393
    +0.05
    0.23
    159
    +0.05
    0.12
    Negative Logits
    actionDate
    -0.48
    idas
    -0.37
    endix
    -0.37
    arching
    -0.36
    athi
    -0.36
    zed
    -0.35
    mand
    -0.35
    ongyang
    -0.35
    ihar
    -0.35
    izu
    -0.34
    POSITIVE LOGITS
     fitt
    0.40
     Invention
    0.40
     bunch
    0.36
     certs
    0.35
     Beasts
    0.33
     surprises
    0.33
     enrichment
    0.33
     worlds
    0.33
     brut
    0.32
     Sequ
    0.32
    Activations Density 7.913%

    No Known Activations