© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 3949
    Prev
    Next
    INDEX
    Explanations

    legal and governmental terms and document sections such as subsections, clauses, and amendments

    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
    314
    +0.07
    0.6%
    316
    +0.07
    0.6%
    283
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.07
    0.03
    416
    +0.07
    0.07
    314
    +0.06
    -0.04
    Negative Logits
     cleaner
    -0.38
    eland
    -0.35
     ultras
    -0.33
     redist
    -0.33
     Solitaire
    -0.32
    opsis
    -0.32
     Ronaldo
    -0.31
     extras
    -0.31
     tours
    -0.31
     passenger
    -0.31
    POSITIVE LOGITS
    umbn
    0.45
    yss
    0.43
    ãĤ¨ãĥ«
    0.41
    ments
    0.41
    MENTS
    0.39
    ursed
    0.39
    votes
    0.38
    itations
    0.38
    vous
    0.38
    Published
    0.38
    Activations Density 6.302%

    No Known Activations