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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 3114
    Prev
    Next
    INDEX
    Explanations

    phrases related to political campaigns and running for office

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "run" in various contexts related to political campaigns or elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ighed
    -0.73
    ippy
    -0.68
     Ryder
    -0.63
    isson
    -0.62
    ":["
    -0.62
     Orbital
    -0.59
     MFT
    -0.58
    EngineDebug
    -0.58
     Oo
    -0.58
    atican
    -0.58
    POSITIVE LOGITS
    clinton
    0.85
     campaigns
    0.83
     mate
    0.82
     candidates
    0.77
     candidacy
    0.75
    agate
    0.74
     candidate
    0.74
    seat
    0.72
    opp
    0.72
    aeda
    0.71
    Activations Density 0.047%

    No Known Activations