© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 19372
    Prev
    Next
    INDEX
    Explanations

    French words or names starting with special characters like ë, ô, and ê

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    frame
    -0.77
    iversity
    -0.71
     vitro
    -0.71
     hitters
    -0.68
    idious
    -0.67
    abase
    -0.67
    iverse
    -0.64
    EStreamFrame
    -0.63
    imore
    -0.61
    ipop
    -0.60
    POSITIVE LOGITS
    ë
    0.98
    ô
    0.98
    ternity
    0.97
    lette
    0.93
    î
    0.92
    ï
    0.85
    tre
    0.84
    rous
    0.81
    ê
    0.80
    lé
    0.79
    Activations Density 0.006%

    No Known Activations