© 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. 7-RES-JB
    11. 17104
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    emotional reactions or expressions of surprise and realization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 7 - surprise

    No Comments

    Negative Logits
    unal
    -0.83
    ullivan
    -0.82
    ciplinary
    -0.74
     occasion
    -0.66
     Flavoring
    -0.66
    aband
    -0.65
     Cosponsors
    -0.63
    cephal
    -0.60
    minist
    -0.60
    ioned
    -0.60
    POSITIVE LOGITS
    ?".
    0.96
    '"
    0.91
    Hey
    0.90
    '."
    0.85
    ?'"
    0.83
    .'"
    0.83
     hey
    0.83
    hey
    0.81
    .")
    0.80
    âĢ¦."
    0.79
    Activations Density 0.160%

    No Known Activations