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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23822
    Prev
    Next
    INDEX
    Explanations

    references to sports teams from Kansas City in particular

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Kansas City and its sports teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.84
    bably
    -0.84
    BOOK
    -0.80
    thood
    -0.79
    nces
    -0.75
    aces
    -0.75
     Scotia
    -0.73
    encers
    -0.71
    ×Ļ×
    -0.70
    cffffcc
    -0.69
    POSITIVE LOGITS
     City
    1.11
    Kansas
    0.91
     Kansas
    0.89
     Wichita
    0.86
    oslov
    0.83
     Republic
    0.82
     Chiefs
    0.81
     State
    0.81
     Rapids
    0.81
     Tornado
    0.80
    Activations Density 0.013%

    No Known Activations