© 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. 10015
    Prev
    Next
    INDEX
    Explanations

    various ingredients and recipes, especially involving chocolate

    oai_token-act-pair · gpt-3.5-turbo

    references to chocolate and dessert 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
     Reeves
    -1.05
    River
    -0.88
     Weld
    -0.84
    Houston
    -0.83
    Dial
    -0.83
    Li
    -0.79
    Lev
    -0.79
    vid
    -0.78
    Xbox
    -0.77
     Technician
    -0.77
    POSITIVE LOGITS
     chocolate
    1.96
     cookies
    1.88
     cookie
    1.78
     cocoa
    1.74
     candy
    1.71
     Cookies
    1.70
     sweets
    1.68
     Cookie
    1.68
     Chocolate
    1.64
     cakes
    1.63
    Activations Density 0.242%

    No Known Activations