© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 18030
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named Lindsey Graham

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Lindsey and mentions of collections or groups of items

    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
    zek
    -0.77
     Ou
    -0.77
    eer
    -0.76
    yip
    -0.74
     cannon
    -0.72
    gob
    -0.70
     Inquisitor
    -0.70
     cannons
    -0.69
    apon
    -0.69
    boys
    -0.69
    POSITIVE LOGITS
     collections
    2.23
     Lindsey
    2.19
     Lindsay
    1.69
     Collections
    1.45
    Lind
    1.06
     Cassidy
    0.95
     Sloan
    0.92
    cci
    0.91
     Kristen
    0.87
    bt
    0.86
    Activations Density 0.029%

    No Known Activations