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. 24229
    Prev
    Next
    INDEX
    Explanations

    phrases related to political control

    oai_token-act-pair · gpt-3.5-turbo

    references to political control and party dominance in government

    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
     Shinji
    -0.64
    lot
    -0.64
     pseudonym
    -0.63
     trader
    -0.63
    eros
    -0.62
     Seraph
    -0.62
    emis
    -0.62
     mathematician
    -0.60
     smugglers
    -0.60
    ãĤ¤ãĥĪ
    -0.60
    POSITIVE LOGITS
     Congress
    1.67
     congress
    1.57
     legislature
    1.54
     legislatures
    1.54
     senate
    1.48
     Legislature
    1.46
     parliament
    1.43
     Senate
    1.43
     Parliament
    1.38
     Assembly
    1.36
    Activations Density 0.202%

    No Known Activations