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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11913
    Prev
    Next
    INDEX
    Explanations

    details related to baking or cooking, particularly focusing on mixing ingredients like batter

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cooking and culinary processes, particularly those involving batter and baking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oot
    -0.76
    ovo
    -0.73
     Vu
    -0.69
    lux
    -0.68
    xus
    -0.68
    NG
    -0.68
     deleted
    -0.67
    Rogue
    -0.65
    ooter
    -0.64
     Conservation
    -0.64
    POSITIVE LOGITS
     batter
    3.34
    urst
    1.91
     batters
    1.80
    rooms
    1.37
     battered
    1.08
     topp
    0.97
    rique
    0.97
    pour
    0.93
     vict
    0.91
     mete
    0.88
    Activations Density 0.038%

    No Known Activations