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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 4663
    Prev
    Next
    INDEX
    Explanations

    conversational fillers or discourse markers used to express surprise, uncertainty, or hesitation

    oai_token-act-pair · gpt-3.5-turbo

    rhetorical questions and expressions of surprise or curiosity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iors
    -0.69
    irie
    -0.68
    iple
    -0.68
    upiter
    -0.67
    uci
    -0.65
     guiActiveUnfocused
    -0.65
    ument
    -0.65
    edom
    -0.64
    escription
    -0.63
    enaries
    -0.63
    POSITIVE LOGITS
     huh
    1.22
     considering
    1.17
     eh
    1.04
    especially
    0.99
     especially
    0.99
     but
    0.94
    but
    0.90
     Especially
    0.87
     frankly
    0.84
     given
    0.82
    Activations Density 0.198%

    No Known Activations