© 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. 5387
    Prev
    Next
    INDEX
    Explanations

    information regarding government policies and actions

    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
    565
    +0.12
    0.6%
    288
    +0.11
    0.5%
    608
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.26
    565
    +0.11
    0.10
    575
    +0.10
    0.15
    Negative Logits
    anwhile
    -0.73
    staking
    -0.70
     Jindal
    -0.65
    imately
    -0.64
    liest
    -0.64
    lain
    -0.63
    arently
    -0.63
    okingly
    -0.62
     Canaver
    -0.61
     Marriott
    -0.60
    POSITIVE LOGITS
    Ms
    0.68
    ãĤ§
    0.65
    isms
    0.64
    Whe
    0.63
    ãĥīãĥ©
    0.62
    tions
    0.60
    izen
    0.60
    ilib
    0.59
    lif
    0.59
    ãĥķãĤ¡
    0.57
    Activations Density 5.755%

    No Known Activations