© 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. 7-RES-JB
    11. 23860
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and courtroom proceedings

    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 @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atism
    -0.83
     [|
    -0.80
    ories
    -0.78
    yip
    -0.77
    olen
    -0.77
    ¥µ
    -0.77
    eful
    -0.76
    efully
    -0.75
    metry
    -0.73
    olulu
    -0.73
    POSITIVE LOGITS
     pled
    0.82
     defendants
    0.80
     sentenced
    0.79
     convicted
    0.78
     defendant
    0.76
     accused
    0.75
     plead
    0.75
     pleaded
    0.69
     rapist
    0.69
     guilty
    0.67
    Activations Density 0.022%

    No Known Activations