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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 3-RES-JB
    6. 22107
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "ait" with varying levels of specificity

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific style of writing or techniques associated with "Kaitlyn" or "Kaitlin."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     segregated
    -0.69
     magnification
    -0.67
    wallet
    -0.60
     sliding
    -0.59
    sword
    -0.58
     glasses
    -0.57
     seeded
    -0.57
     Borders
    -0.55
     homeland
    -0.55
    requires
    -0.54
    POSITIVE LOGITS
    ait
    1.00
    anya
    0.99
    oun
    0.92
    anooga
    0.91
    ani
    0.83
    os
    0.80
    rack
    0.78
    ois
    0.77
    chet
    0.77
    ons
    0.76
    Activations Density 0.010%

    No Known Activations