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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5804
    Prev
    Next
    INDEX
    Explanations

    instructions related to baking or cooking

    oai_token-act-pair · gpt-3.5-turbo

    cooking instructions and related culinary actions

    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
    icz
    -0.78
    anmar
    -0.71
    alloc
    -0.67
    女
    -0.67
    VID
    -0.67
    Leon
    -0.66
    agy
    -0.65
    SIGN
    -0.63
    DEF
    -0.61
    years
    -0.61
    POSITIVE LOGITS
     mixture
    0.94
     remaining
    0.89
     lid
    0.84
     your
    0.82
     skillet
    0.81
     oven
    0.80
     evenly
    0.75
     halves
    0.73
     each
    0.73
    semble
    0.72
    Activations Density 0.073%

    No Known Activations