© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10134
    Prev
    Next
    INDEX
    Explanations

    words related to hairstyles, specifically foamy or fluffy hair described as "fro" or "frothy"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fro" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ually
    -0.78
    roit
    -0.69
    yard
    -0.66
    ual
    -0.65
    monton
    -0.64
    itory
    -0.64
    Solution
    -0.61
    illa
    -0.61
    iple
    -0.60
    Page
    -0.60
    POSITIVE LOGITS
    thing
    1.07
    thy
    1.06
    bled
    0.91
    sts
    0.87
    mph
    0.82
    bered
    0.82
    zed
    0.78
    ates
    0.78
    ated
    0.78
    dden
    0.77
    Activations Density 0.073%

    No Known Activations