© 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. 8-RES-JB
    11. 2079
    Prev
    Next
    INDEX
    Explanations

    words related to dogs and specific locations like "Miami", "South Beach", "Kansas City Royals"

    oai_token-act-pair · gpt-3.5-turbo

    important nouns and their relationships in a sentence, often reflecting cultural or geographic themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ".[
    -0.90
    ."[
    -0.83
    RESULTS
    -0.81
    .""
    -0.79
    "],"
    -0.76
    andowski
    -0.76
     ÂŃ
    -0.75
    ãĢij
    -0.75
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.73
    ''.
    -0.72
    POSITIVE LOGITS
     underrated
    0.91
    ounty
    0.73
    erenn
    0.68
    ensibly
    0.66
     staple
    0.64
     dudes
    0.63
     Featuring
    0.62
     powerhouse
    0.61
    eaturing
    0.61
    enic
    0.61
    Activations Density 1.247%

    No Known Activations