© 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. 18950
    Prev
    Next
    INDEX
    Explanations

    proper names of political figures and locations

    oai_token-act-pair · gpt-3.5-turbo

    names of notable politicians and their affiliations

    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
     Hebdo
    -0.85
     Kinnikuman
    -0.78
     Sahara
    -0.75
    rawdownloadcloneembedreportprint
    -0.75
     Dhabi
    -0.74
     Penguin
    -0.71
    DragonMagazine
    -0.71
     civilisation
    -0.69
     Guardiola
    -0.68
     Shanghai
    -0.64
    POSITIVE LOGITS
    Senate
    1.19
     senate
    1.05
     Senate
    1.03
     senators
    1.01
     filib
    0.94
     veto
    0.93
    cong
    0.92
    aucus
    0.91
     reelection
    0.90
     filibuster
    0.90
    Activations Density 0.149%

    No Known Activations