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. 0-RES-JB
    6. 21476
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual, likely a prominent figure or someone involved in news events

    oai_token-act-pair · gpt-3.5-turbo

    names or surnames, particularly of individuals involved in significant 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
     Tropical
    -0.65
     reconstruction
    -0.65
     inclusive
    -0.65
     healing
    -0.61
     resting
    -0.59
     rest
    -0.59
     rested
    -0.58
     Sandy
    -0.58
     completed
    -0.57
     tot
    -0.57
    POSITIVE LOGITS
    kov
    4.51
    akov
    1.65
    hov
    1.62
    chenko
    1.59
    chev
    1.49
    nikov
    1.49
    kos
    1.42
    bourg
    1.35
    kowski
    1.33
    sov
    1.33
    Activations Density 0.011%

    No Known Activations