© 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 EvalsExportsinterp-engineNEWAPI 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. 5298
    Prev
    Next
    INDEX
    Explanations

    Legal terms and court proceedings

    oai_token-act-pair · gpt-3.5-turbo

    legal terms and references related to court proceedings

    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
     labeling
    -0.80
    aucuses
    -0.80
    DonaldTrump
    -0.79
     enrollment
    -0.74
    achev
    -0.73
    Washington
    -0.72
    ASHINGTON
    -0.72
    ¨
    -0.72
     "#
    -0.72
    ospons
    -0.72
    POSITIVE LOGITS
     Tribunal
    1.28
    Judge
    1.24
     Judge
    1.20
     tribunal
    1.20
     adjourn
    1.20
     barr
    1.19
    Prosecut
    1.18
     QC
    1.17
     jury
    1.16
     judge
    1.14
    Activations Density 0.229%

    No Known Activations