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. 10-RES-JB
    6. 212
    Prev
    Next
    INDEX
    Explanations

    phrases related to political ideologies advocating certain principles or values

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to political advocacy and ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.81
     Radar
    -0.77
    ptoms
    -0.74
    laughs
    -0.73
     Ples
    -0.72
    Laughs
    -0.71
    wat
    -0.69
    adelphia
    -0.68
    Buzz
    -0.67
     Billboard
    -0.66
    POSITIVE LOGITS
     equality
    1.46
     neutrality
    1.37
     egalitarian
    1.35
     openness
    1.31
     tolerance
    1.30
     fairness
    1.28
     moderation
    1.26
    clus
    1.26
     abstinence
    1.26
     purity
    1.24
    Activations Density 0.353%

    No Known Activations