© 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. 11-RES-JB
    11. 9959
    Prev
    Next
    INDEX
    Explanations

    hesitations or pauses in speech

    oai_token-act-pair · gpt-3.5-turbo

    filler words and hesitations in speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Preview
    -0.66
    Adds
    -0.63
    STDOUT
    -0.61
    icipated
    -0.61
    IAL
    -0.61
    avers
    -0.60
     RIS
    -0.59
    Published
    -0.57
    INC
    -0.57
    accessible
    -0.56
    POSITIVE LOGITS
    mmm
    1.34
     huh
    1.25
    ahah
    1.17
     oh
    1.13
    mmmm
    1.11
    hhh
    1.04
     yeah
    1.04
    hhhh
    1.00
    hh
    0.97
    mm
    0.96
    Activations Density 0.039%

    No Known Activations