Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12660
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or sports teams related to the city of Buffalo

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the location "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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egal
    -0.93
    ially
    -0.86
    olation
    -0.75
     accur
    -0.72
    arget
    -0.71
    olated
    -0.70
    aunder
    -0.70
    heid
    -0.69
    enemy
    -0.69
    Mach
    -0.68
    POSITIVE LOGITS
     Sabres
    1.14
     Niagara
    1.10
     Trace
    1.08
     Bills
    1.06
    halla
    0.84
    town
    0.78
     Springfield
    0.78
    ĵĺ
    0.77
    illac
    0.77
     Buffalo
    0.76
    Activations Density 0.007%

    No Known Activations