© 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. 20146
    Prev
    Next
    INDEX
    Explanations

    references to the name "Jud."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jud" and its various forms

    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
     Helsinki
    -0.77
    ulton
    -0.75
    URRENT
    -0.73
    company
    -0.73
    Interstitial
    -0.70
     Afric
    -0.69
    join
    -0.69
    natureconservancy
    -0.69
    change
    -0.67
    ãĥĨãĤ£
    -0.65
    POSITIVE LOGITS
     Jud
    1.21
    iciary
    1.20
    Jud
    1.16
    icial
    1.12
    gement
    1.12
    gment
    1.11
    jud
    1.08
    gments
    0.95
    ging
    0.92
    paio
    0.85
    Activations Density 0.011%

    No Known Activations