© 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. 39920
    Prev
    Next
    INDEX
    Explanations

    words related to programming, specifically focusing on blocks of code or code structures

    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
    +0.20
    0.8%
    361
    +0.17
    0.7%
    35
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.16
    651
    +0.17
    0.10
    361
    +0.15
    0.08
    Negative Logits
     reluct
    -0.90
     Ples
    -0.84
    rouse
    -0.82
    llers
    -0.82
     Norn
    -0.82
     Echoes
    -0.82
     dishon
    -0.79
    vind
    -0.79
     Opportun
    -0.77
     Ves
    -0.77
    POSITIVE LOGITS
    busters
    1.60
    quote
    1.52
    buster
    1.41
    chains
    1.20
    aded
    1.20
    ades
    1.15
    ade
    1.13
    ading
    1.11
    chain
    1.03
    aders
    1.03
    Activations Density 4.383%

    No Known Activations