© 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. 10-RES-JB
    11. 9977
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures, specifically President-elect Donald Trump

    oai_token-act-pair · gpt-3.5-turbo

    references to political candidates, particularly the term "President-elect" associated with Donald Trump

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MpServer
    -0.87
    PG
    -0.63
     Animals
    -0.62
    MQ
    -0.61
    REL
    -0.61
    wl
    -0.60
     provinces
    -0.60
     qualitative
    -0.59
     Prairie
    -0.59
    FG
    -0.59
    POSITIVE LOGITS
     Donald
    1.30
     Trump
    1.15
     TRUMP
    1.03
    Donald
    0.98
     Barack
    0.92
    Trump
    0.92
     Rodrigo
    0.91
     Narendra
    0.91
    trump
    0.90
    realDonaldTrump
    0.90
    Activations Density 0.030%

    No Known Activations