© 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. 7031
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking or running for re-election or 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 @ 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
    Ku
    -0.74
    erial
    -0.73
    Magikarp
    -0.72
    osphere
    -0.70
    oken
    -0.69
    Detailed
    -0.69
     Liver
    -0.69
    atomic
    -0.67
    ken
    -0.66
    Family
    -0.65
    POSITIVE LOGITS
    eering
    1.11
     campaigns
    0.99
     reelection
    0.97
     candidate
    0.91
     campaign
    0.86
    cand
    0.86
     commissions
    0.85
     bids
    0.84
    visor
    0.83
     candidates
    0.81
    Activations Density 0.032%

    No Known Activations