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. 0-RES-JB
    6. 24242
    Prev
    Next
    INDEX
    Explanations

    words related to a specific person or entity, likely a political figure named Trudeau

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those related to politics or news events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     orgasm
    -0.73
     nursing
    -0.71
     KS
    -0.68
     innings
    -0.65
    iga
    -0.64
     indefinite
    -0.62
     AFC
    -0.62
     CoC
    -0.61
     exert
    -0.61
     congress
    -0.61
    POSITIVE LOGITS
    Tr
    3.71
    tr
    2.25
     Tr
    1.94
    trace
    1.59
    Track
    1.49
    TR
    1.46
    Tracker
    1.41
    Trade
    1.31
     tr
    1.30
    Tra
    1.28
    Activations Density 0.017%

    No Known Activations