© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 12125
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings or courts of law

    oai_token-act-pair · gpt-3.5-turbo

    terms related to judicial or legal proceedings, especially tribunals and arbitration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VP
    -0.74
    ku
    -0.73
    javascript
    -0.65
     Extrem
    -0.65
     Weld
    -0.63
    kell
    -0.61
    young
    -0.61
     Gillespie
    -0.59
     lush
    -0.59
    ften
    -0.59
    POSITIVE LOGITS
     tribunal
    1.31
     Tribunal
    1.09
     hearings
    0.91
    naire
    0.87
     proceedings
    0.79
    Court
    0.77
     arbit
    0.76
     ruled
    0.75
     court
    0.75
    mbudsman
    0.74
    Activations Density 0.008%

    No Known Activations