Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23341
    Prev
    Next
    INDEX
    Explanations

    moments expressing a pause or reflection in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to time-related pauses or reflective moments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grades
    -0.70
    uces
    -0.69
     scores
    -0.68
    agles
    -0.64
     subordinates
    -0.62
     fitt
    -0.62
    kefeller
    -0.62
    licts
    -0.62
    comes
    -0.62
    models
    -0.62
    POSITIVE LOGITS
     glance
    0.82
    aire
    0.79
     pause
    0.77
     apiece
    0.76
    hander
    0.74
     ago
    0.73
     lick
    0.69
    ary
    0.69
    glass
    0.68
    hower
    0.68
    Activations Density 0.075%

    No Known Activations