© 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. 10-RES-JB
    11. 13926
    Prev
    Next
    INDEX
    Explanations

    terms related to legal processes, specifically the issuance of subpoenas

    oai_token-act-pair · gpt-3.5-turbo

    references to subpoenas and legal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocks
    -0.73
    stocks
    -0.72
    adjust
    -0.71
    istically
    -0.71
    other
    -0.69
    ock
    -0.69
    essim
    -0.67
    luaj
    -0.65
    deals
    -0.65
    opsy
    -0.65
    POSITIVE LOGITS
     subpoen
    1.18
     subpoena
    1.16
    aed
    0.87
     compel
    0.74
    illin
    0.74
     summons
    0.72
    ENCY
    0.72
     Lerner
    0.71
     unse
    0.70
     Citation
    0.70
    Activations Density 0.057%

    No Known Activations