© 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. 10-RES-JB
    11. 7844
    Prev
    Next
    INDEX
    Explanations

    references to sports teams or players from Cleveland

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Cleveland sports teams and players

    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
    wana
    -0.76
    zai
    -0.74
    uador
    -0.72
    ledged
    -0.72
    inen
    -0.71
    ded
    -0.71
     Tasman
    -0.69
    nob
    -0.69
    ging
    -0.69
    sent
    -0.68
    POSITIVE LOGITS
     Cavaliers
    1.36
     Clinic
    1.25
     Browns
    1.23
     Heights
    1.06
     Indians
    1.03
     Cleveland
    0.95
     Plain
    0.89
     Ohio
    0.85
     Hopkins
    0.84
     Cavs
    0.83
    Activations Density 0.031%

    No Known Activations