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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 34183
    Prev
    Next
    INDEX
    Explanations

    specific names or entities related to business and politics

    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
    +0.34
    1.9%
    481
    +0.10
    0.6%
    423
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    693
    +0.34
    0.14
    423
    +0.10
    0.16
    288
    +0.08
    0.30
    Negative Logits
    pletion
    -0.52
    escription
    -0.51
    BTC
    -0.49
     completion
    -0.48
    FILE
    -0.47
    ocious
    -0.47
    LIST
    -0.47
    Afee
    -0.43
     fil
    -0.42
    Son
    -0.42
    POSITIVE LOGITS
     circles
    0.74
    lance
    0.71
     legislatures
    0.69
     classrooms
    0.67
     Indies
    0.66
    abouts
    0.65
    ecd
    0.63
     contexts
    0.61
     kitchens
    0.61
     Democr
    0.59
    Activations Density 18.355%

    No Known Activations