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. 3-RES-JB
    6. 21884
    Prev
    Next
    INDEX
    Explanations

    the name "Lance" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Lance."

    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
    worldly
    -0.81
    determination
    -0.78
    sbm
    -0.75
    SpaceEngineers
    -0.74
    morrow
    -0.73
    ItemTracker
    -0.73
    urated
    -0.72
    icism
    -0.71
    displayText
    -0.71
    alien
    -0.71
    POSITIVE LOGITS
    lot
    1.20
     Lance
    1.06
     Armstrong
    1.05
     Corpor
    0.97
     Daniels
    0.83
     Oliver
    0.82
     Redd
    0.80
     Stephenson
    0.79
     Harvey
    0.77
     Bott
    0.76
    Activations Density 0.008%

    No Known Activations