© 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 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. 33431
    Prev
    Next
    INDEX
    Explanations

    references to specific names, potentially related to news articles or reports

    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
    343
    +0.08
    0.6%
    187
    +0.07
    0.5%
    183
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    712
    +0.08
    0.04
    48
    +0.07
    0.08
    343
    +0.07
    0.07
    Negative Logits
    ently
    -0.43
    handedly
    -0.40
    shock
    -0.38
    ysis
    -0.37
     cooker
    -0.36
    externalActionCode
    -0.36
    desc
    -0.36
    Ingredients
    -0.35
     brokers
    -0.34
     Horton
    -0.34
    POSITIVE LOGITS
    cha
    0.71
    glers
    0.57
    istical
    0.55
    lass
    0.54
    ãĤ¤ãĥĪ
    0.51
     Talent
    0.50
    hers
    0.49
    luck
    0.49
    ãĥ¼
    0.49
    mingham
    0.48
    Activations Density 7.478%

    No Known Activations