© 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. 0-RES-JB
    11. 2513
    Prev
    Next
    INDEX
    Explanations

    references to sprays, particularly related to vandalism, self-defense, medical treatment, and household use

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of spray

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verning
    -0.79
     Religious
    -0.67
    mund
    -0.66
    Economic
    -0.65
    ylum
    -0.64
    bitcoin
    -0.64
    Political
    -0.64
     Marriage
    -0.64
    orem
    -0.64
    lishes
    -0.64
    POSITIVE LOGITS
     spray
    3.88
     Spray
    2.74
     sprayed
    2.29
     spraying
    2.29
     aeros
    1.50
    Spr
    1.47
     spr
    1.46
    spr
    1.36
     graffiti
    1.24
     paint
    1.24
    Activations Density 0.006%

    No Known Activations