© 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. 115
    Prev
    Next
    INDEX
    Explanations

    information related to the sugar industry

    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
    739
    +0.23
    0.7%
    288
    +0.21
    0.7%
    326
    +0.20
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.23
    0.09
    288
    +0.21
    0.11
    99
    +0.20
    0.06
    Negative Logits
    atche
    -1.16
    naire
    -1.15
    ative
    -1.15
    naires
    -1.12
    orate
    -1.07
     Tsarnaev
    -1.06
    Ģ
    -1.04
    ership
    -1.04
     NCT
    -1.03
    iation
    -1.02
    POSITIVE LOGITS
     cane
    1.61
     syrup
    1.47
     beet
    1.46
    moon
    1.28
    heart
    1.21
    comb
    1.17
     mell
    1.17
    kered
    1.14
    ptive
    1.13
     daddy
    1.13
    Activations Density 1.643%

    No Known Activations