© 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. 3656
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    expressions of astonishment or surprise

    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
    BOOK
    -0.81
     Enhancement
    -0.81
    Guard
    -0.80
     Converted
    -0.80
     Journals
    -0.77
     Franch
    -0.75
    IUM
    -0.73
    actionDate
    -0.72
    âĶģ
    -0.71
    heimer
    -0.69
    POSITIVE LOGITS
    anging
    0.90
    azard
    0.82
    undreds
    0.77
     dear
    0.75
     darn
    0.72
    oh
    0.71
     mute
    0.70
    oho
    0.70
     od
    0.66
    entimes
    0.66
    Activations Density 0.009%

    No Known Activations