© 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 EvalsExportsAPI 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. 7-RES-JB
    11. 20605
    Prev
    Next
    INDEX
    Explanations

    references to baked goods, particularly bread

    oai_token-act-pair · gpt-3.5-turbo

    references to types of bread and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uate
    -0.86
    uating
    -0.73
     Cheong
    -0.72
    uated
    -0.72
     Nevada
    -0.69
     Panthers
    -0.69
    igious
    -0.68
    ities
    -0.68
     Scientology
    -0.67
    ARP
    -0.66
    POSITIVE LOGITS
    fruit
    1.12
    grain
    1.05
    cr
    1.04
    winner
    1.03
    sticks
    1.01
     pudding
    0.99
     dough
    0.95
    nut
    0.95
    wallet
    0.92
     bread
    0.91
    Activations Density 0.018%

    No Known Activations