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. 40214
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical regions and discussions on regional influence and collaboration

    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
    1.1%
    288
    +0.15
    0.7%
    302
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    616
    +0.23
    0.08
    160
    +0.15
    0.14
    623
    +0.13
    0.06
    Negative Logits
    ertodd
    -1.01
    vous
    -0.97
    selage
    -0.87
    uden
    -0.84
    --+
    -0.81
    rette
    -0.79
    Ö¼
    -0.77
    edin
    -0.77
    cellent
    -0.77
    âĸĪâĸĪâĸĪâĸĪ
    -0.76
    POSITIVE LOGITS
    ities
    0.99
    ized
    0.95
     parks
    0.90
    ised
    0.89
     offices
    0.87
    ization
    0.87
     governments
    0.85
     alliances
    0.85
     capitals
    0.85
     variations
    0.85
    Activations Density 5.370%

    No Known Activations