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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 14518
    Prev
    Next
    INDEX
    Explanations

    phrases related to political campaigns and elections

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to the Democratic Party and its candidates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agnar
    -0.74
    Ry
    -0.72
    icles
    -0.70
    affles
    -0.68
    ted
    -0.67
    uria
    -0.64
    utherford
    -0.63
     Tob
    -0.62
    ridges
    -0.62
    olkien
    -0.62
    POSITIVE LOGITS
     Party
    1.26
     National
    1.00
     nominee
    0.95
     Caucus
    0.91
     Congressional
    0.90
     frontrunner
    0.89
     nomination
    0.89
     Governors
    0.88
     nomine
    0.85
     Primary
    0.85
    Activations Density 0.048%

    No Known Activations