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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 6669
    Prev
    Next
    INDEX
    Explanations

    American cities related to sports teams

    oai_token-act-pair · gpt-3.5-turbo

    names of geographical locations, particularly cities

    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
    enegger
    -0.86
    schild
    -0.72
     dx
    -0.71
    bara
    -0.71
     Zup
    -0.71
    aird
    -0.69
    haar
    -0.69
    cribed
    -0.69
     Cosponsors
    -0.69
     ministerial
    -0.68
    POSITIVE LOGITS
     Athletics
    1.05
     Athletic
    0.96
     Falcons
    0.96
     Wolves
    0.94
     Giants
    0.94
     Jets
    0.93
     teammate
    0.93
     Buccaneers
    0.92
     Eagles
    0.91
     rookie
    0.89
    Activations Density 0.083%

    No Known Activations