© 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. 0-RES-JB
    11. 16591
    Prev
    Next
    INDEX
    Explanations

    references to legal cases or defendants in legal contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to defendants in a legal context

    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
    ahime
    -0.65
    oots
    -0.64
    flow
    -0.63
     McMaster
    -0.63
    etry
    -0.60
    ularity
    -0.59
     Unle
    -0.58
    ageddon
    -0.57
    ULAR
    -0.57
    ivation
    -0.57
    POSITIVE LOGITS
     defendant
    3.43
     defendants
    3.42
     Defendants
    2.75
     Defendant
    2.69
     plaintiff
    2.56
     plaintiffs
    2.28
     Plaintiff
    2.07
     Plaint
    1.82
     appellant
    1.80
     petitioner
    1.64
    Activations Density 0.013%

    No Known Activations