© 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. 9-RES-JB
    11. 18030
    Prev
    Next
    INDEX
    Explanations

    sentences related to working with or mentioning dough

    oai_token-act-pair · gpt-3.5-turbo

    references to different types of dough and flour in a cooking context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eve
    -0.75
    nesota
    -0.70
     apost
    -0.69
    NetMessage
    -0.69
    76561
    -0.68
     Bans
    -0.68
    ued
    -0.66
    audi
    -0.65
     Amon
    -0.62
    elist
    -0.60
    POSITIVE LOGITS
    nut
    1.62
    nuts
    1.62
    boys
    1.09
    ishes
    0.98
    ty
    0.93
    roll
    0.85
    awan
    0.84
    balls
    0.82
    meal
    0.79
    riter
    0.77
    Activations Density 0.072%

    No Known Activations