© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 14244
    Prev
    Next
    INDEX
    Explanations

    the word "incumbent."

    oai_token-act-pair · gpt-3.5-turbo

    references to incumbents in political contexts

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

    No Comments

    Negative Logits
    wagen
    -1.04
    gas
    -0.87
    anguage
    -0.84
    mberg
    -0.83
    apa
    -0.82
    okin
    -0.82
    stocks
    -0.82
    oho
    -0.81
    hod
    -0.81
    ooter
    -0.80
    POSITIVE LOGITS
     incumbent
    1.13
     challenger
    0.92
     incumb
    0.89
     challengers
    0.83
     frontrunner
    0.81
     loser
    0.79
     favourites
    0.76
     stal
    0.73
     nem
    0.72
     foe
    0.71
    Activations Density 0.013%

    No Known Activations