© 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. 14955
    Prev
    Next
    INDEX
    Explanations

    references to U.S. governmental entities and legal proceedings

    oai_token-act-pair · gpt-3.5-turbo

    references to the U.S. government and its officials

    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
    esson
    -0.73
    quickShipAvailable
    -0.70
    lets
    -0.69
     boil
    -0.68
     temptation
    -0.67
    ebook
    -0.65
     concentrated
    -0.64
    enhagen
    -0.63
    eware
    -0.63
     bec
    -0.62
    POSITIVE LOGITS
     Airways
    1.14
     Postal
    1.13
     Cellular
    1.13
     Citizenship
    1.09
     Marshal
    1.06
     Army
    1.00
     Geological
    1.00
     Attorney
    0.97
     Patent
    0.97
    ADA
    0.96
    Activations Density 0.066%

    No Known Activations