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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45077
    Prev
    Next
    INDEX
    Explanations

    references to Broadway-related content

    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
    +0.12
    0.8%
    288
    +0.09
    0.6%
    484
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.18
    326
    +0.09
    0.20
    649
    +0.08
    0.03
    Negative Logits
    ascript
    -0.54
    uala
    -0.52
    arians
    -0.49
    ively
    -0.49
    erate
    -0.49
    ivated
    -0.47
    vironment
    -0.47
    oras
    -0.46
    onomous
    -0.45
    ministic
    -0.45
    POSITIVE LOGITS
     Theatre
    0.53
    lyn
    0.49
     productions
    0.48
     Harbour
    0.47
     Theater
    0.47
    Ward
    0.47
     Broadway
    0.47
     Melody
    0.47
     Dreams
    0.46
     Revival
    0.46
    Activations Density 7.154%

    No Known Activations