© 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. 1-RES-JB
    11. 1000
    Prev
    Next
    INDEX
    Explanations

    disfluencies and hesitant speech markers such as 'uh', 'huh'

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hesitation or filler words in conversation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.87
    flies
    -0.81
    ãĥ¯ãĥ³
    -0.74
    IENT
    -0.73
    BILITY
    -0.73
    xual
    -0.73
    ãģ®å
    -0.71
    ãĥ´
    -0.70
    updated
    -0.70
     ILCS
    -0.68
    POSITIVE LOGITS
     huh
    1.18
     uh
    1.00
     Huh
    0.97
     pardon
    0.85
     oh
    0.83
    lease
    0.83
     Uh
    0.79
     Fellow
    0.76
    mmm
    0.76
     eh
    0.75
    Activations Density 0.007%

    No Known Activations