© 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. 8-RES-JB
    11. 15183
    Prev
    Next
    INDEX
    Explanations

    names of specific stadium locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various stadiums

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bery
    -0.73
    dit
    -0.71
    bart
    -0.67
    luaj
    -0.64
    nir
    -0.63
    ushima
    -0.63
    tail
    -0.62
    uten
    -0.62
    ãĥ©ãĥ³
    -0.62
    uscript
    -0.61
    POSITIVE LOGITS
     stadiums
    1.11
     stadium
    1.02
     Stadium
    0.88
    adium
    0.80
     announcer
    0.77
    Built
    0.73
     amph
    0.72
     seating
    0.71
     turf
    0.69
     scoreboard
    0.68
    Activations Density 0.055%

    No Known Activations