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. 10-RES-JB
    6. 11712
    Prev
    Next
    INDEX
    Explanations

    terms related to political and legal controversies, such as recounts, bans, server investigations, and anthem protests

    oai_token-act-pair · gpt-3.5-turbo

    references to political controversies and legal actions, particularly those involving travel bans, recounts, and email servers

    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
    umar
    -0.81
    uner
    -0.80
    DragonMagazine
    -0.74
    Balt
    -0.71
    hiro
    -0.67
    uckland
    -0.66
    NW
    -0.66
     Flavoring
    -0.66
    Lear
    -0.65
    Marx
    -0.65
    POSITIVE LOGITS
     controversy
    0.81
     controversies
    0.77
     violation
    0.76
     violates
    0.72
     unconstitutional
    0.70
     laws
    0.70
     âĢķ
    0.70
     Nieto
    0.67
     Sioux
    0.67
    ADVERTISEMENT
    0.66
    Activations Density 0.193%

    No Known Activations