© 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. 22007
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or safety-related discussions

    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
     Maul
    -0.95
     Cree
    -0.93
     zoo
    -0.89
     elephants
    -0.83
     Uganda
    -0.82
     Ai
    -0.81
     humming
    -0.79
     plac
    -0.78
     Zimbabwe
    -0.76
     VC
    -0.76
    POSITIVE LOGITS
     Brady
    2.45
     Patriots
    2.04
     Belichick
    1.97
     Pats
    1.94
     Gron
    1.80
    ichick
    1.73
     Amend
    1.48
     Kraft
    1.46
     Goodell
    1.33
     Patriot
    1.21
    Activations Density 0.148%

    No Known Activations