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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 21505
    Prev
    Next
    INDEX
    Explanations

    information related to the preparation and usage of materials in various contexts, such as cooking, building, and crafting

    oai_token-act-pair · gpt-3.5-turbo

    recommendations or guidelines related to food preparation and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     StarCraft
    -0.75
     eSports
    -0.75
     existential
    -0.71
     esports
    -0.71
     Gamergate
    -0.71
     Voting
    -0.70
    href
    -0.69
     Esports
    -0.69
    language
    -0.69
     Marxist
    -0.69
    POSITIVE LOGITS
     moisture
    1.17
     thickness
    1.02
     thicker
    0.99
     drying
    0.98
     pH
    0.98
     silicone
    0.97
     adhesive
    0.96
     waterproof
    0.96
     dried
    0.95
     PVC
    0.94
    Activations Density 1.121%

    No Known Activations