© 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. 0-RES-JB
    11. 11426
    Prev
    Next
    INDEX
    Explanations

    mentions of bipartisan support or unity

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sections or appendices in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maxwell
    -0.72
    berra
    -0.65
    catentry
    -0.65
    ngth
    -0.64
    atters
    -0.64
    obyl
    -0.64
    arya
    -0.62
    advertising
    -0.61
    artisan
    -0.61
     blaster
    -0.61
    POSITIVE LOGITS
     put
    0.87
    Wire
    0.72
    wire
    0.70
     Doe
    0.65
     lug
    0.65
     paraph
    0.64
    type
    0.62
    nik
    0.61
    lude
    0.61
     McGr
    0.60
    Activations Density 0.000%

    No Known Activations