© 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. 1-RES-JB
    11. 11326
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and defendants

    oai_token-act-pair · gpt-3.5-turbo

    references to defendants in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    drive
    -0.76
    QL
    -0.72
     Direction
    -0.68
    region
    -0.66
    olen
    -0.65
    HAHA
    -0.65
    nz
    -0.64
     Mass
    -0.63
    FU
    -0.63
     Fork
    -0.63
    POSITIVE LOGITS
     defendants
    1.14
     defendant
    0.83
     Defendants
    0.83
     indicted
    0.82
     accused
    0.80
    ervatives
    0.80
     plaintiffs
    0.77
     filings
    0.77
     pled
    0.77
    ensen
    0.74
    Activations Density 0.007%

    No Known Activations