© 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 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. 11-RES-JB
    11. 14910
    Prev
    Next
    INDEX
    Explanations

    references to political figures and legal cases

    oai_token-act-pair · gpt-3.5-turbo

    key events and statements related to legal cases involving prominent figures

    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
     mosqu
    -1.01
     Rubio
    -0.99
    Rub
    -0.98
     Hung
    -0.96
     rabbits
    -0.93
    Hung
    -0.93
     Budapest
    -0.92
     Dracula
    -0.89
     synagogue
    -0.87
     Hungary
    -0.86
    POSITIVE LOGITS
     Manning
    2.39
     Bradley
    1.38
     Eli
    1.20
     WikiLeaks
    1.15
     Peyton
    1.06
    Army
    1.04
     Army
    1.02
     soldier
    1.02
     Wikileaks
    0.98
     whistlebl
    0.96
    Activations Density 0.115%

    No Known Activations