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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 3796
    Prev
    Next
    INDEX
    Explanations

    mentions of "pill"

    oai_token-act-pair · gpt-3.5-turbo

    references to pills and pharmaceutical products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.82
    REDACTED
    -0.77
    elist
    -0.72
    auga
    -0.71
    worldly
    -0.68
     Giuliani
    -0.68
    SPONSORED
    -0.67
     Kislyak
    -0.64
     Talent
    -0.61
     Democr
    -0.61
    POSITIVE LOGITS
    ows
    1.34
    oried
    1.25
    aging
    1.12
    iard
    0.99
    ayers
    0.95
    aged
    0.95
    arding
    0.94
    age
    0.94
    ager
    0.94
    agers
    0.93
    Activations Density 0.044%

    No Known Activations