© 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. 10-RES-JB
    6. 884
    Prev
    Next
    INDEX
    Explanations

    references to the city of Buffalo, specifically Buffalo Wild Wings and sports teams like the Buffalo Bills and Buffalo Sabres

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Buffalo" in various contexts related to sports and branding

    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
    ICES
    -0.85
    ESA
    -0.81
    ially
    -0.77
    nces
    -0.74
    pmwiki
    -0.73
    egal
    -0.72
    heid
    -0.72
    enemy
    -0.71
    inen
    -0.70
    olate
    -0.70
    POSITIVE LOGITS
     Sabres
    1.35
     Niagara
    1.26
     Bills
    1.22
     Trace
    1.07
     Wild
    0.91
     Buffalo
    0.89
     Grove
    0.88
     Springfield
    0.87
     buffalo
    0.80
     Bore
    0.78
    Activations Density 0.031%

    No Known Activations