© 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. 0-RES-JB
    6. 5099
    Prev
    Next
    INDEX
    Explanations

    mentions of sports teams or universities named "Buffalo"

    oai_token-act-pair · gpt-3.5-turbo

    references to Buffalo and its associated sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IS
    -0.75
    DOM
    -0.75
    isl
    -0.74
    icit
    -0.74
    sol
    -0.70
    omal
    -0.69
     Sol
    -0.68
    ilit
    -0.66
    iser
    -0.66
     sol
    -0.64
    POSITIVE LOGITS
     Buffalo
    3.68
    Buff
    2.40
     buffalo
    2.07
     Sabres
    2.03
     Niagara
    1.87
     Erie
    1.83
     Bills
    1.82
     Albany
    1.73
     Syracuse
    1.68
     Rochester
    1.66
    Activations Density 0.019%

    No Known Activations