© 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. 45734
    Prev
    Next
    INDEX
    Explanations

    functions and code snippets related to sending email messages and handling app state changes

    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
    +0.31
    1.3%
    393
    +0.21
    0.9%
    739
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.31
    0.25
    43
    +0.21
    0.12
    418
    +0.13
    0.14
    Negative Logits
    avorite
    -0.85
    entimes
    -0.84
    itational
    -0.77
    iasis
    -0.73
    natureconservancy
    -0.73
    conom
    -0.72
    alysis
    -0.71
     glim
    -0.70
    wana
    -0.70
    enance
    -0.69
    POSITIVE LOGITS
     sizeof
    1.08
     "\
    0.96
     uint
    0.86
     lambda
    0.86
     etc
    0.85
     null
    0.85
    )"
    0.85
     /*
    0.83
     0
    0.82
    ioch
    0.82
    Activations Density 8.075%

    No Known Activations