© 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. 20952
    Prev
    Next
    INDEX
    Explanations

    legal language related to penalties and regulations, including financial penalties and imprisonment terms

    oai_token-act-pair · gpt-3.5-turbo

    legal terms and conditions related to penalties and responsibilities

    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
    pictured
    -0.79
    mma
    -0.74
    elight
    -0.71
    skirts
    -0.70
     Oops
    -0.68
     Roose
    -0.66
     Goodbye
    -0.66
    eva
    -0.62
    thanks
    -0.61
    erb
    -0.61
    POSITIVE LOGITS
    :(
    1.26
     subparagraph
    1.12
     such
    1.01
     notwithstanding
    0.99
     subsection
    0.99
    '';
    0.99
    ''.
    0.98
     ``(
    0.97
     hereby
    0.95
     bona
    0.94
    Activations Density 0.181%

    No Known Activations