© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 15737
    Prev
    Next
    INDEX
    Explanations

    mentions of recipe titles and adaptations in a text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of recipes

    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
    lasses
    -0.84
    osc
    -0.73
    etheless
    -0.66
    porting
    -0.65
    ials
    -0.65
    Īè
    -0.65
    nesota
    -0.64
    enth
    -0.63
    arton
    -0.63
    ases
    -0.62
    POSITIVE LOGITS
    Ingredients
    1.01
     recipe
    0.97
     recipes
    0.91
    Recipe
    0.90
     booklet
    0.88
     ingredients
    0.85
     adapted
    0.84
    reci
    0.82
     ingredient
    0.78
     substit
    0.77
    Activations Density 0.051%

    No Known Activations