© 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. 10-RES-JB
    11. 18929
    Prev
    Next
    INDEX
    Explanations

    titles or acronyms related to government positions or legal professions

    oai_token-act-pair · gpt-3.5-turbo

    references to government officials and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enhagen
    -0.82
     wip
    -0.71
    esson
    -0.70
    ebook
    -0.68
     concentrated
    -0.67
     temptation
    -0.65
     negatively
    -0.65
     favour
    -0.64
    addons
    -0.64
     boil
    -0.63
    POSITIVE LOGITS
     Attorney
    1.08
     Citizenship
    1.07
     Airways
    1.07
     Cellular
    1.05
     Postal
    0.99
     Marshal
    0.99
    ADA
    0.94
     Geological
    0.93
    GI
    0.92
     Army
    0.92
    Activations Density 0.079%

    No Known Activations