© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 16337
    Prev
    Next
    INDEX
    Explanations

    mentions of legal terms and court cases

    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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ür
    -0.84
    ories
    -0.83
    olen
    -0.78
    yip
    -0.75
     [|
    -0.75
    efully
    -0.75
    uilt
    -0.73
    eful
    -0.72
    atism
    -0.72
    iHUD
    -0.71
    POSITIVE LOGITS
     pled
    0.85
     defendants
    0.82
     defendant
    0.81
     plead
    0.79
     Defendant
    0.77
     accused
    0.77
     convicted
    0.76
     sentenced
    0.76
    eering
    0.73
     guilty
    0.71
    Activations Density 0.008%

    No Known Activations