© 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. 2-RES-JB
    11. 9300
    Prev
    Next
    INDEX
    Explanations

    mentions of political positions, specifically related to elections

    oai_token-act-pair · gpt-3.5-turbo

    references to electoral politics, particularly related to mayoral and gubernatorial races

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anamo
    -0.96
     McGee
    -0.82
    enment
    -0.81
    bell
    -0.79
    hof
    -0.76
    zsche
    -0.74
    ORGE
    -0.73
    Downloadha
    -0.73
    rette
    -0.72
     Schwar
    -0.71
    POSITIVE LOGITS
     mayoral
    1.09
     election
    0.96
     elections
    0.91
     councils
    0.90
    cand
    0.90
     borough
    0.88
    ¥ŀ
    0.88
     candidate
    0.87
     candidates
    0.86
     hopeful
    0.86
    Activations Density 0.010%

    No Known Activations