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. 11-RES-JB
    6. 15291
    Prev
    Next
    INDEX
    Explanations

    clothing and fashion-related terms, especially related to colors and styles

    oai_token-act-pair · gpt-3.5-turbo

    details about distinctive visual characteristics and descriptions of items

    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
    missions
    -1.06
    ravings
    -1.06
    facts
    -1.03
    sites
    -1.02
    events
    -1.00
    abilities
    -0.99
    Players
    -0.98
    awatts
    -0.98
    Reports
    -0.97
    votes
    -0.97
    POSITIVE LOGITS
     version
    1.12
     pair
    1.04
     piece
    1.03
     paperback
    1.03
     sweater
    0.98
     sized
    0.98
     flashlight
    0.97
     bottle
    0.96
     loaf
    0.95
     replica
    0.95
    Activations Density 0.244%

    No Known Activations