© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 19164
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual, John Kerry

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific political figures, particularly John Kerry

    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
    pi
    -0.73
    ãĥ´ãĤ¡
    -0.71
    ãĢ
    -0.70
     monop
    -0.70
    onga
    -0.67
     transform
    -0.66
    azon
    -0.66
    orc
    -0.65
     pi
    -0.65
     div
    -0.63
    POSITIVE LOGITS
     Kerry
    3.82
     McCain
    1.47
     Gerry
    1.42
     Kasich
    1.34
    erry
    1.29
     Gore
    1.25
     Biden
    1.25
     Kaine
    1.20
     Kissinger
    1.17
     Kendall
    1.17
    Activations Density 0.014%

    No Known Activations