© 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. 2-RES-JB
    11. 22541
    Prev
    Next
    INDEX
    Explanations

    references to the Republican strategist Karl Rove

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific political figures and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ambers
    -0.82
    isters
    -0.81
    ococ
    -0.78
    ivism
    -0.77
    ocks
    -0.76
    utes
    -0.75
    uador
    -0.74
    atsu
    -0.70
    ancouver
    -0.70
    reprene
    -0.70
    POSITIVE LOGITS
     Rove
    1.21
     Dire
    0.94
    wolves
    0.91
    wolf
    0.90
     Ratt
    0.83
     cones
    0.82
    nces
    0.80
    wald
    0.78
    bil
    0.76
    tto
    0.76
    Activations Density 0.015%

    No Known Activations