© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3434
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning a judge's actions or involvement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of judges or related titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rivals
    -0.76
    rolet
    -0.75
    ulus
    -0.72
    ontent
    -0.71
     Horde
    -0.68
    uld
    -0.65
     Thieves
    -0.65
    haar
    -0.64
    irth
    -0.63
     Decay
    -0.62
    POSITIVE LOGITS
     presiding
    1.33
     overseeing
    1.13
     rulings
    1.04
     Gorsuch
    0.99
     Advocate
    0.98
    jud
    0.93
     ruled
    0.92
     sentenced
    0.90
    rooms
    0.89
    redd
    0.89
    Activations Density 0.058%

    No Known Activations