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. 22735
    Prev
    Next
    INDEX
    Explanations

    words related to political controversies and scandals

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political movements and controversies

    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
     Sul
    -0.78
    gob
    -0.77
    amina
    -0.75
     Bulg
    -0.73
     Nanto
    -0.73
    auder
    -0.71
     Osw
    -0.70
    addle
    -0.70
    ij士
    -0.70
     Acer
    -0.69
    POSITIVE LOGITS
     fiasco
    1.09
    âĦ¢
    1.00
     debacle
    1.00
     supporters
    0.96
     proponents
    0.96
     controversy
    0.95
     repeal
    0.93
     protests
    0.92
     Implementation
    0.90
     hearings
    0.89
    Activations Density 0.250%

    No Known Activations