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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 22586
    Prev
    Next
    INDEX
    Explanations

    references to specific stadiums or venues

    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 @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abet
    -0.78
    remlin
    -0.74
    leans
    -0.74
    onyms
    -0.71
    bart
    -0.69
    ativity
    -0.68
    thodox
    -0.68
    yan
    -0.65
    ILA
    -0.64
    Balt
    -0.64
    POSITIVE LOGITS
     Stadium
    1.30
     stadium
    0.92
     Plaza
    0.91
     stadiums
    0.85
     Authority
    0.80
     Grounds
    0.78
     Facilities
    0.76
     Auditor
    0.75
     Hub
    0.74
     Sporting
    0.74
    Activations Density 0.015%

    No Known Activations