© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12444
    Prev
    Next
    INDEX
    Explanations

    phrases expressing surprise or curiosity

    oai_token-act-pair · gpt-3.5-turbo

    expressions of incredulity or disbelief

    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
    ettel
    -0.71
    arbon
    -0.70
    aeper
    -0.69
    aditional
    -0.67
    alach
    -0.66
    ategory
    -0.66
    iosis
    -0.66
    berman
    -0.65
    undo
    -0.64
    ictionary
    -0.64
    POSITIVE LOGITS
     why
    0.95
     WHY
    0.78
    why
    0.76
     coincidence
    0.73
     aloud
    0.73
     Flavoring
    0.71
     whatsoever
    0.67
    REDACTED
    0.67
     Puzz
    0.66
     wonder
    0.66
    Activations Density 0.011%

    No Known Activations