© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5361
    Prev
    Next
    INDEX
    Explanations

    words related to legal settings, specifically focusing on occurrences within a courtroom

    oai_token-act-pair · gpt-3.5-turbo

    references to courtrooms and legal settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subs
    -0.66
    gans
    -0.61
     Trip
    -0.61
    Repl
    -0.60
     (-
    -0.59
     AQ
    -0.58
    mods
    -0.58
    Posts
    -0.58
     replen
    -0.57
    inator
    -0.56
    POSITIVE LOGITS
     courtroom
    3.74
     courthouse
    2.57
     court
    1.73
    Court
    1.69
    Judge
    1.69
     Court
    1.57
     judicial
    1.55
     jurors
    1.51
     COURT
    1.49
     jury
    1.47
    Activations Density 0.020%

    No Known Activations