© 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. 10-RES-JB
    11. 13552
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings, especially hearings

    oai_token-act-pair · gpt-3.5-turbo

    references to hearings or legal proceedings

    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
    jac
    -0.78
    acea
    -0.69
    romeda
    -0.67
     Haram
    -0.66
    ecd
    -0.63
    football
    -0.63
    obal
    -0.63
    zu
    -0.62
    spr
    -0.62
    rave
    -0.62
    POSITIVE LOGITS
     hearings
    1.22
     examiner
    1.18
     proceedings
    1.04
     transcripts
    1.04
     testimony
    1.04
     convened
    1.03
     adjourn
    0.96
     hearing
    0.96
     held
    0.89
     Hearing
    0.89
    Activations Density 0.041%

    No Known Activations