© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20289
    Prev
    Next
    INDEX
    Explanations

    surprising events or discoveries

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "surprising" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etary
    -0.73
    istar
    -0.73
    eret
    -0.61
    halla
    -0.61
     Duty
    -0.61
    wid
    -0.60
    peg
    -0.59
     PAT
    -0.59
    istan
    -0.59
    ati
    -0.59
    POSITIVE LOGITS
     surprising
    3.41
     shocking
    2.11
     unexpected
    2.05
     startling
    2.02
     surprise
    1.99
     surprises
    1.86
     surprisingly
    1.82
     puzzling
    1.71
     surprised
    1.66
     remarkable
    1.65
    Activations Density 0.016%

    No Known Activations