© 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. 34724
    Prev
    Next
    INDEX
    Explanations

    events and actions in a narrative context

    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
    +0.36
    1.9%
    393
    +0.18
    1.0%
    481
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.36
    0.28
    546
    +0.18
    0.17
    43
    +0.14
    0.16
    Negative Logits
    ãĥ¥
    -0.68
    è£ħ
    -0.64
    quartered
    -0.62
    ãĤ´ãĥ³
    -0.61
    Cause
    -0.61
    alogy
    -0.58
    SourceFile
    -0.58
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.54
    ãĤ¢ãĥ«
    -0.54
    Pool
    -0.53
    POSITIVE LOGITS
     however
    0.84
     somew
    0.79
     alas
    0.74
     though
    0.68
     we
    0.65
     lest
    0.65
     whenever
    0.61
     when
    0.58
     confronted
    0.58
     thankfully
    0.57
    Activations Density 11.028%

    No Known Activations