© 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. 3870
    Prev
    Next
    INDEX
    Explanations

    terms related to critique and philosophical analysis

    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
    267
    +0.14
    0.6%
    644
    +0.14
    0.6%
    178
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.08
    651
    +0.14
    0.05
    555
    +0.12
    0.04
    Negative Logits
    velt
    -1.08
    loo
    -0.91
    pora
    -0.86
    UTH
    -0.72
    gypt
    -0.69
    noon
    -0.69
     hyd
    -0.69
    holders
    -0.69
     discipline
    -0.68
     Warm
    -0.68
    POSITIVE LOGITS
    erion
    1.60
    iques
    1.33
    ique
    1.31
    icism
    1.25
    eria
    1.16
    iqu
    1.11
    ically
    1.04
    iants
    1.02
    icals
    0.94
    erb
    0.92
    Activations Density 0.702%

    No Known Activations