© 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. 9-RES-JB
    11. 22703
    Prev
    Next
    INDEX
    Explanations

    statements expressing negation or refutation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating permanence or continuity

    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
     antioxid
    -0.83
     portfolios
    -0.71
    Leaks
    -0.70
    BP
    -0.58
     PsyNet
    -0.58
     WARN
    -0.57
     rapidly
    -0.57
     Supplemental
    -0.57
     Essential
    -0.56
    hoe
    -0.56
    POSITIVE LOGITS
    theless
    0.97
     nor
    0.88
    rences
    0.87
    ukong
    0.75
    thood
    0.75
    before
    0.73
     dime
    0.73
    uth
    0.72
     dreamed
    0.70
    ratch
    0.70
    Activations Density 0.152%

    No Known Activations