© 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 Local
    9. 6-RES_SCL-AJT
    11. 40398
    Prev
    Next
    INDEX
    Explanations

    locations and political events

    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
    675
    +0.14
    0.6%
    154
    +0.13
    0.6%
    69
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.14
    0.24
    154
    +0.13
    0.23
    48
    +0.12
    0.19
    Negative Logits
     Bigfoot
    -0.80
     paperback
    -0.78
     subconscious
    -0.78
     Lovecraft
    -0.77
     chronological
    -0.77
     philosophers
    -0.76
     fiction
    -0.76
     Fiction
    -0.75
     Nietzsche
    -0.74
     adventures
    -0.73
    POSITIVE LOGITS
    sic
    1.11
    abad
    1.01
    said
    1.01
    cu
    0.92
    READ
    0.90
    older
    0.90
    ï¸ı
    0.89
    tar
    0.88
    tal
    0.87
    beit
    0.86
    Activations Density 3.062%

    No Known Activations