© 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. 19666
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Dom" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "domino."

    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
    packing
    -0.82
    UGH
    -0.66
    ="#
    -0.63
    WAYS
    -0.62
    journal
    -0.62
     arrow
    -0.61
    keeper
    -0.61
     mars
    -0.61
    SEE
    -0.60
     arrows
    -0.60
    POSITIVE LOGITS
    ino
    1.28
    inant
    1.20
    estic
    1.16
    ination
    1.14
    ains
    1.14
    inating
    1.08
    aine
    1.04
    inos
    0.97
    inate
    0.96
    inal
    0.96
    Activations Density 0.037%

    No Known Activations