© 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. 13591
    Prev
    Next
    INDEX
    Explanations

    legal terminology or court-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to legal outcomes or decisions

    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
     arom
    -0.81
    meal
    -0.81
    gall
    -0.80
    nell
    -0.80
     Allaah
    -0.77
     Dund
    -0.75
    aign
    -0.74
    erville
    -0.73
    dl
    -0.70
     Boyd
    -0.70
    POSITIVE LOGITS
    Super
    2.33
     Super
    2.28
    super
    2.23
     SUPER
    2.09
     super
    2.08
     Sup
    1.81
    SUP
    1.52
     supers
    1.51
    sup
    1.46
    Sup
    1.44
    Activations Density 0.202%

    No Known Activations