© 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. 12-RES-JB
    11. 3290
    Prev
    Next
    INDEX
    Explanations

    legal terms related to lawsuits and prosecution

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to legal actions and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    udder
    -0.88
    20439
    -0.84
    oops
    -0.81
    aunt
    -0.81
    ucket
    -0.78
    utherford
    -0.77
    America
    -0.77
    izzle
    -0.77
    ergus
    -0.76
    addle
    -0.76
    POSITIVE LOGITS
     Azerbai
    1.14
     Bulgarian
    1.10
     municipality
    1.05
     Sloven
    1.00
     organis
    1.00
     Hungarian
    0.99
     Croatian
    0.99
     Serbian
    0.99
     Romanian
    0.97
     Finnish
    0.96
    Activations Density 1.050%

    No Known Activations