Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 34551
    Prev
    Next
    INDEX
    Explanations

    information related to educational organizations and legal issues, specifically focusing on a specific individual named Gulen

    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
    +0.12
    0.6%
    377
    +0.10
    0.6%
    299
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.21
    683
    +0.10
    0.11
    299
    +0.08
    0.12
    Negative Logits
     Wales
    -0.55
     Hots
    -0.51
     imaging
    -0.49
    \<
    -0.48
     Speedway
    -0.48
     Welsh
    -0.47
     Imaging
    -0.47
     breakdown
    -0.47
    alth
    -0.47
     range
    -0.46
    POSITIVE LOGITS
    mud
    0.83
    zar
    0.78
    zeb
    0.74
    bling
    0.74
    marg
    0.72
    istani
    0.70
    gur
    0.70
    pin
    0.69
    ulp
    0.69
    renheit
    0.68
    Activations Density 6.891%

    No Known Activations