© 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. 6-RES-JB
    11. 7190
    Prev
    Next
    INDEX
    Explanations

    references to political candidates

    oai_token-act-pair · gpt-3.5-turbo

    mentions of candidates in a political context

    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
    orgetown
    -0.83
    alam
    -0.74
    vironment
    -0.73
    cest
    -0.73
    iencies
    -0.71
    erie
    -0.71
    oho
    -0.68
    oise
    -0.68
    ijk
    -0.68
    ews
    -0.68
    POSITIVE LOGITS
     candidates
    1.03
    cand
    1.01
    idates
    1.00
     candidate
    0.90
    Cand
    0.87
     vying
    0.81
     Candidate
    0.79
     voters
    0.77
     ballots
    0.72
     campaigns
    0.71
    Activations Density 0.031%

    No Known Activations