© 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. 13646
    Prev
    Next
    INDEX
    Explanations

    dates, events, and schedules

    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
    +0.34
    1.7%
    314
    +0.10
    0.5%
    289
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.34
    0.21
    6
    +0.10
    0.29
    314
    +0.09
    -0.02
    Negative Logits
     nodd
    -0.85
    ensical
    -0.78
     glim
    -0.74
     Citiz
    -0.72
     encount
    -0.70
     condem
    -0.67
     unbeliev
    -0.66
     exha
    -0.65
     surpr
    -0.65
     skelet
    -0.65
    POSITIVE LOGITS
    £
    0.78
    ????
    0.76
    $
    0.75
    unknown
    0.74
    âĸº
    0.73
    ..
    0.72
    ---
    0.71
    etc
    0.71
    Sac
    0.70
    âĨij
    0.70
    Activations Density 17.733%

    No Known Activations