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. 1-RES-JB
    6. 11982
    Prev
    Next
    INDEX
    Explanations

    terms related to lobbying activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "lobbying" and related discussions about influence and expenditures in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Carbuncle
    -0.83
    orah
    -0.75
    thia
    -0.68
    pron
    -0.67
     Rapt
    -0.67
     Ath
    -0.67
     Chosen
    -0.66
     Reincarn
    -0.66
    cond
    -0.65
    ebook
    -0.65
    POSITIVE LOGITS
     lobbying
    1.28
     lobbied
    0.96
     lobbyist
    0.93
     lobbyists
    0.92
     lobby
    0.89
     lobb
    0.88
     councill
    0.83
    aukee
    0.79
     furiously
    0.75
    rieve
    0.75
    Activations Density 0.007%

    No Known Activations