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. 6-RES-JB
    6. 18106
    Prev
    Next
    INDEX
    Explanations

    words related to political leadership positions with a focus on "Majority Leader"

    oai_token-act-pair · gpt-3.5-turbo

    references to political leadership roles and majorities in the Senate

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zsche
    -0.88
    icular
    -0.83
    angible
    -0.80
    raltar
    -0.77
    oho
    -0.75
    entric
    -0.74
    ãĤ¨ãĥ«
    -0.73
    Äĩ
    -0.73
    uckland
    -0.73
    iverpool
    -0.73
    POSITIVE LOGITS
     Leader
    1.13
     Whip
    0.99
     Majority
    0.95
     Mitch
    0.88
     Clerk
    0.80
     Reid
    0.80
    Leader
    0.80
     Task
    0.79
     Administration
    0.78
     Chair
    0.78
    Activations Density 0.029%

    No Known Activations