© 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. 20256
    Prev
    Next
    INDEX
    Explanations

    names of political figures, particularly focusing on Donald Trump and Hillary Clinton

    oai_token-act-pair · gpt-3.5-turbo

    references to Donald Trump and Hillary Clinton in discussions about politics

    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
    -0.75
    awks
    -0.73
    à¨
    -0.71
    âĵĺ
    -0.67
    akings
    -0.66
     Weir
    -0.65
    lights
    -0.65
    products
    -0.62
    Pur
    -0.61
    Ir
    -0.61
    POSITIVE LOGITS
     Jr
    1.31
     Sr
    1.05
    Jr
    0.94
     Donald
    0.93
     campaigned
    0.89
     supporters
    0.85
     Presidential
    0.84
     Hillary
    0.84
     (@
    0.78
     supporter
    0.78
    Activations Density 0.100%

    No Known Activations