© 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. 6-RES-JB
    11. 4935
    Prev
    Next
    INDEX
    Explanations

    mentions of seeking or running for re-election

    oai_token-act-pair · gpt-3.5-turbo

    references to elections and reelections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osphere
    -0.72
     Beckham
    -0.68
    Origin
    -0.67
    Border
    -0.66
    ALT
    -0.66
    Ku
    -0.66
    ANG
    -0.64
    ãĤ·
    -0.63
     Wond
    -0.62
    quart
    -0.62
    POSITIVE LOGITS
     campaigns
    1.00
     reelection
    0.94
     candidacy
    0.87
    eering
    0.87
     campaign
    0.87
     candidate
    0.87
     bids
    0.87
    election
    0.86
     commissions
    0.85
     candidates
    0.83
    Activations Density 0.041%

    No Known Activations