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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 19166
    Prev
    Next
    INDEX
    Explanations

    terms related to political and social issues, such as campaigns, relief efforts, nonprofit organizations, government spending, and criminal charges

    oai_token-act-pair · gpt-3.5-turbo

    terms related to voting, political campaigns, and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    agonist
    -0.76
    agame
    -0.74
    yip
    -0.72
    ouf
    -0.72
    xual
    -0.72
    abase
    -0.69
    porter
    -0.66
    endment
    -0.65
    ACTED
    -0.65
    maxwell
    -0.64
    POSITIVE LOGITS
     offerings
    1.09
     structures
    1.00
     contests
    1.00
     titles
    1.00
     initiatives
    0.97
     formations
    0.96
     programs
    0.95
     tracts
    0.95
     rosters
    0.94
     outfits
    0.94
    Activations Density 0.620%

    No Known Activations