Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 229
    Prev
    Next
    INDEX
    Explanations

    references to political figures, specifically senators

    oai_token-act-pair · gpt-3.5-turbo

    references to senators, particularly in the context of political discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ember
    -0.74
    PK
    -0.61
    emaker
    -0.61
    &
    -0.57
     ©
    -0.57
    ifle
    -0.56
    eval
    -0.56
     performance
    -0.56
    ifter
    -0.55
    £
    -0.55
    POSITIVE LOGITS
     senators
    3.67
     Senators
    2.72
     senator
    2.46
     senate
    2.12
    Senator
    2.10
     Senate
    2.04
     lawmakers
    2.01
     Senator
    2.01
     legislators
    1.98
    Senate
    1.97
    Activations Density 0.013%

    No Known Activations