© 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. 8-RES-JB
    11. 12316
    Prev
    Next
    INDEX
    Explanations

    legal terms related to 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 @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     everywhere
    -0.77
     trickle
    -0.76
     sustainability
    -0.75
     UX
    -0.75
     migr
    -0.72
     optim
    -0.70
     bookmark
    -0.70
     emulation
    -0.70
     visibility
    -0.69
     welcome
    -0.69
    POSITIVE LOGITS
    Prosecutors
    1.72
    Prosecut
    1.65
    Court
    1.60
    Judge
    1.51
     Prosecutors
    1.45
     defendants
    1.38
    Attorney
    1.33
     defendant
    1.33
     Defendant
    1.33
     jurors
    1.29
    Activations Density 0.493%

    No Known Activations