© 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. 10169
    Prev
    Next
    INDEX
    Explanations

    instructions for baking recipes

    oai_token-act-pair · gpt-3.5-turbo

    phrases and instructions related to baking and cookie preparation

    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
     Chronic
    -0.72
     Morph
    -0.72
     impairment
    -0.71
     Nanto
    -0.69
    VID
    -0.68
    Effects
    -0.68
     Acquisition
    -0.65
    Benz
    -0.64
    Mit
    -0.64
     suppressed
    -0.64
    POSITIVE LOGITS
     parchment
    1.31
     pastry
    1.27
     dough
    1.18
     baking
    1.14
     evenly
    1.12
     batter
    1.07
     seam
    1.06
     rectangle
    1.06
     crust
    1.05
     cookie
    1.04
    Activations Density 0.177%

    No Known Activations