© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 15435
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, specifically the Toronto Blue Jays and other related teams

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific colored sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    schild
    -0.96
    enegger
    -0.94
     Duterte
    -0.81
    chwitz
    -0.77
    é¾įå¥ij士
    -0.76
     Shutterstock
    -0.76
     Idle
    -0.75
    è£ħ
    -0.71
     Hobby
    -0.71
     Milo
    -0.71
    POSITIVE LOGITS
    hawks
    1.20
    seys
    1.16
     Devils
    1.11
    birds
    1.09
     Eagles
    1.09
    agles
    1.09
     Bears
    1.08
     Panthers
    1.07
     Wolves
    1.06
     Lions
    1.06
    Activations Density 0.215%

    No Known Activations