© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 1211
    Prev
    Next
    INDEX
    Explanations

    and highlight instructions related to saving, downloading, and altering files or software configurations

    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
    640
    +0.12
    0.5%
    321
    +0.11
    0.5%
    57
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    531
    +0.12
    0.03
    321
    +0.11
    0.03
    402
    +0.11
    0.03
    Negative Logits
     Scythe
    -0.83
    enberg
    -0.74
    isms
    -0.73
    enburg
    -0.72
    atic
    -0.71
    ranch
    -0.70
    aurus
    -0.69
     Randolph
    -0.69
     Blossom
    -0.68
    paio
    -0.67
    POSITIVE LOGITS
    uploads
    0.79
    ICT
    0.78
    Instance
    0.74
    UGC
    0.72
    UV
    0.72
    TING
    0.71
    ãģŁ
    0.68
    lishing
    0.68
    ressing
    0.67
     loaded
    0.67
    Activations Density 0.267%

    No Known Activations