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

    Neuronpedia

    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. 2-RES-JB
    11. 23744
    Prev
    Next
    INDEX
    Explanations

    expressions related to silence or lack of speech

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and discussions surrounding the concept of silence

    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
    isin
    -0.71
    amins
    -0.70
    xon
    -0.69
    agers
    -0.69
    issue
    -0.68
    dri
    -0.68
    ramid
    -0.67
    drivers
    -0.67
    shi
    -0.66
    arel
    -0.65
    POSITIVE LOGITS
     silence
    1.08
     Silence
    1.04
    rences
    0.99
    etooth
    0.80
    creen
    0.78
    ences
    0.78
     silenced
    0.76
     cooker
    0.72
    fulness
    0.71
     silent
    0.70
    Activations Density 0.010%

    No Known Activations