© 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. 34037
    Prev
    Next
    INDEX
    Explanations

    various instances of the word 'proven'

    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
    435
    +0.10
    0.5%
    731
    +0.09
    0.5%
    332
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.10
    0.09
    622
    +0.09
    0.06
    362
    +0.08
    0.09
    Negative Logits
    umbn
    -0.68
    alon
    -0.67
    utterstock
    -0.62
    achu
    -0.58
    ummer
    -0.56
    IDES
    -0.56
    hops
    -0.55
    querade
    -0.55
    regate
    -0.55
    chief
    -0.55
    POSITIVE LOGITS
    iferation
    0.79
     proven
    0.76
    icity
    0.71
    iary
    0.71
     debunked
    0.68
    edly
    0.64
    icist
    0.63
    ibly
    0.62
    ãĥ¼ãĥĨ
    0.61
     refuted
    0.60
    Activations Density 8.756%

    No Known Activations