© 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. 34783
    Prev
    Next
    INDEX
    Explanations

    references to individuals, their actions, and accomplishments within a specific 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
    +0.18
    0.8%
    659
    +0.11
    0.5%
    525
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.18
    0.16
    525
    +0.11
    0.10
    547
    +0.10
    0.06
    Negative Logits
    Maria
    -0.80
    cknowled
    -0.68
     Petra
    -0.65
     cogn
    -0.64
     CLS
    -0.63
    rative
    -0.63
     Madame
    -0.63
     Mae
    -0.63
     Veronica
    -0.62
    uate
    -0.62
    POSITIVE LOGITS
     Sr
    0.97
     QC
    0.93
     Jr
    0.93
    enegger
    0.90
    ovich
    0.87
     III
    0.82
    fman
    0.82
    steen
    0.80
    agher
    0.78
    espie
    0.75
    Activations Density 4.336%

    No Known Activations