© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 3873
    Prev
    Next
    INDEX
    Explanations

    code syntax and parameters in a software environment

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    +0.39
    1.6%
    255
    +0.12
    0.5%
    217
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    739
    +0.39
    0.06
    356
    +0.12
    0.01
    727
    +0.11
    0.06
    Negative Logits
    halla
    -0.78
    icity
    -0.75
    ulously
    -0.71
    olitan
    -0.70
    aband
    -0.68
    Ħ¢
    -0.67
    agraph
    -0.66
     sanctioned
    -0.66
    innie
    -0.64
    enge
    -0.64
    POSITIVE LOGITS
    Loader
    0.83
    wine
    0.79
    Guest
    0.70
     Cake
    0.70
    Mer
    0.70
     Moor
    0.69
     [-
    0.69
     Tend
    0.68
     Proxy
    0.68
     subp
    0.68
    Activations Density 7.130%

    No Known Activations