© 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. 11-RES-JB
    11. 1823
    Prev
    Next
    INDEX
    Explanations

    mentioned instances of riot and related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to riots and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stellar
    -0.66
    ĻĤ
    -0.63
    IPP
    -0.62
    hare
    -0.60
     Yosemite
    -0.60
    hran
    -0.59
     Copy
    -0.59
    DonaldTrump
    -0.58
     continents
    -0.57
    omething
    -0.57
    POSITIVE LOGITS
    ous
    1.18
    ously
    0.98
    rained
    0.93
    ing
    0.91
    osity
    0.90
    ers
    0.89
     riot
    0.89
    naire
    0.87
    eering
    0.86
     police
    0.83
    Activations Density 0.048%

    No Known Activations