© 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. 2-RES-JB
    11. 23976
    Prev
    Next
    INDEX
    Explanations

    the interjection "Uh"

    oai_token-act-pair · gpt-3.5-turbo

    utterances or interjections indicative of pauses or hesitation in speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.84
    milo
    -0.83
    egal
    -0.82
    ãģ®å®
    -0.79
    xual
    -0.78
    IUM
    -0.76
    NetMessage
    -0.75
    eus
    -0.73
    ROR
    -0.73
    hester
    -0.72
    POSITIVE LOGITS
    Ħ¢
    0.79
     Uh
    0.77
     uh
    0.76
     huh
    0.71
     oh
    0.68
     Robb
    0.65
     pardon
    0.65
    pps
    0.65
     Huh
    0.64
    entimes
    0.64
    Activations Density 0.011%

    No Known Activations