© 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. 4-RES-JB
    11. 18349
    Prev
    Next
    INDEX
    Explanations

    mentions of the animal "squirrel"

    oai_token-act-pair · gpt-3.5-turbo

    references to squirrels

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

    No Comments

    Negative Logits
     Archdemon
    -0.93
    SPONSORED
    -0.83
    vious
    -0.64
    claimed
    -0.62
    plan
    -0.62
    anza
    -0.62
    hower
    -0.62
    cious
    -0.61
    )=(
    -0.60
    $$
    -0.60
    POSITIVE LOGITS
    irrel
    1.07
     squirrel
    0.95
     monkeys
    0.91
     Squirrel
    0.89
    sburg
    0.85
    ruff
    0.83
    abies
    0.80
    rats
    0.80
    oleon
    0.80
    reys
    0.79
    Activations Density 0.011%

    No Known Activations