© 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. 1-RES-JB
    11. 919
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the term 'lobbyists'

    oai_token-act-pair · gpt-3.5-turbo

    references to lobbyists and lobbying activities

    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
    -0.76
    Condition
    -0.75
    forth
    -0.71
    resp
    -0.71
    grain
    -0.71
    cond
    -0.71
    condition
    -0.70
    birth
    -0.70
    Course
    -0.69
     Incarnation
    -0.69
    POSITIVE LOGITS
     lobbyist
    1.26
     lobbyists
    1.19
     lobbying
    1.09
     lobb
    0.90
    loo
    0.89
     lobbied
    0.88
     droid
    0.87
     lobby
    0.81
     Lobby
    0.78
     councill
    0.76
    Activations Density 0.005%

    No Known Activations