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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6834
    Prev
    Next
    INDEX
    Explanations

    the word "stick" followed by other specific words like "carrot", indicating an analogy or comparison

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "stick" in various contexts

    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
     unfocusedRange
    -0.75
    actionDate
    -0.73
     suites
    -0.69
    KEN
    -0.65
    Export
    -0.63
    bered
    -0.62
     Cannes
    -0.62
    odes
    -0.61
     Nept
    -0.60
    gdala
    -0.60
    POSITIVE LOGITS
    iness
    1.09
    holder
    1.04
    lers
    0.97
    holders
    0.95
    handle
    0.94
    handled
    0.89
    manship
    0.88
    river
    0.87
    figure
    0.83
    gers
    0.83
    Activations Density 0.031%

    No Known Activations