© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 5324
    Prev
    Next
    INDEX
    Explanations

    information related to geographic locations and events happening in those locations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    640
    +0.16
    0.6%
    393
    +0.15
    0.6%
    408
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.16
    0.10
    123
    +0.15
    0.09
    362
    +0.14
    0.10
    Negative Logits
    oulos
    -1.08
    henko
    -0.99
    ouble
    -0.92
    untled
    -0.90
    STAR
    -0.88
    ratulations
    -0.88
    angel
    -0.87
     sooner
    -0.85
     awa
    -0.84
    abis
    -0.84
    POSITIVE LOGITS
     Nanto
    1.06
     southwest
    1.05
     whence
    0.98
     flats
    0.98
     Var
    0.97
     northwest
    0.97
     northeast
    0.95
     Bald
    0.94
     NW
    0.94
     southeast
    0.93
    Activations Density 1.960%

    No Known Activations