© 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. 3617
    Prev
    Next
    INDEX
    Explanations

    legal and judicial terms

    oai_token-act-pair · gpt-3.5-turbo

    references to legal actions or investigations related to governmental agencies

    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
    ãĤ¨ãĥ«
    -1.06
    Í
    -0.94
    ãĥŁ
    -0.88
    iour
    -0.86
    ãĥĺ
    -0.85
    reci
    -0.84
     à¨
    -0.82
    ãĥİ
    -0.78
    ãĤ¤
    -0.77
    Ïī
    -0.77
    POSITIVE LOGITS
     Judicial
    1.66
     DOJ
    1.65
     FOIA
    1.64
     congressional
    1.56
     subpoen
    1.50
     Holder
    1.41
     Congressional
    1.41
     Grassley
    1.39
     Attorney
    1.39
     ACLU
    1.38
    Activations Density 0.495%

    No Known Activations