© 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. 35111
    Prev
    Next
    INDEX
    Explanations

    names of political figures and organizations

    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
    447
    +0.23
    1.4%
    761
    +0.10
    0.6%
    442
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.23
    0.08
    111
    +0.10
    0.06
    578
    +0.10
    0.02
    Negative Logits
     Kov
    -0.54
    fit
    -0.50
     includ
    -0.50
    ertodd
    -0.48
    aeus
    -0.47
    undo
    -0.47
    berman
    -0.45
    oret
    -0.45
    Running
    -0.45
    Beat
    -0.44
    POSITIVE LOGITS
    igion
    0.72
    nces
    0.64
    chell
    0.62
    senal
    0.57
    loo
    0.55
    itage
    0.54
    lees
    0.53
    jri
    0.53
    unning
    0.52
    llah
    0.52
    Activations Density 13.087%

    No Known Activations