© 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. 5526
    Prev
    Next
    INDEX
    Explanations

    expressions of belief or belief-related statements

    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
    679
    +0.14
    0.5%
    644
    +0.14
    0.5%
    566
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.14
    0.12
    177
    +0.14
    0.08
    536
    +0.12
    0.07
    Negative Logits
    lore
    -0.87
    basketball
    -0.78
    voy
    -0.73
    inse
    -0.73
    rake
    -0.72
    ebook
    -0.71
    else
    -0.71
     Peninsula
    -0.69
    ifle
    -0.69
    ancial
    -0.68
    POSITIVE LOGITS
    ħ
    0.99
     strongly
    0.98
    §
    0.97
    ¿½
    0.97
     obliged
    0.93
     obligated
    0.92
     passionately
    0.89
     compelled
    0.89
     unres
    0.89
    ¥
    0.84
    Activations Density 1.483%

    No Known Activations