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. 3-RES-JB
    6. 21965
    Prev
    Next
    INDEX
    Explanations

    keywords related to political leadership, particularly within the Republican Party

    oai_token-act-pair · gpt-3.5-turbo

    references to political leadership and organizational structures within the Republican Party

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çIJ
    -0.72
    IFF
    -0.69
    ionic
    -0.65
     Atlantis
    -0.62
    DragonMagazine
    -0.62
    autical
    -0.61
    anuts
    -0.61
    artifacts
    -0.61
    ificial
    -0.61
    Graphics
    -0.60
    POSITIVE LOGITS
    Democrats
    0.80
     Caucus
    0.79
     moderates
    0.76
    Republicans
    0.75
    eers
    0.73
     factions
    0.73
    legates
    0.73
     Darrell
    0.72
    eering
    0.72
    hester
    0.71
    Activations Density 0.386%

    No Known Activations