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. 10-RES-JB
    6. 1530
    Prev
    Next
    INDEX
    Explanations

    instructions or steps in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to food preparation and serving

    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
     Gamergate
    -0.69
    ForgeModLoader
    -0.63
     Aerospace
    -0.62
     Fundamental
    -0.61
     metic
    -0.61
     Hz
    -0.60
     Sanford
    -0.60
     Journals
    -0.59
    sighted
    -0.59
     mechanics
    -0.59
    POSITIVE LOGITS
     garn
    1.21
     salad
    1.18
     gravy
    1.16
     topp
    1.12
     veggies
    1.11
     grilled
    1.11
     salads
    1.11
     servings
    1.09
     topped
    1.08
     salsa
    1.08
    Activations Density 0.197%

    No Known Activations