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. 1-RES-JB
    6. 4484
    Prev
    Next
    INDEX
    Explanations

    references to a sports team named "Lions"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Detroit Lions football team

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elsius
    -0.95
     srf
    -0.95
    mble
    -0.89
    lly
    -0.88
    ntil
    -0.84
     Seym
    -0.77
    irt
    -0.76
    irlf
    -0.75
    EStream
    -0.74
    leanor
    -0.74
    POSITIVE LOGITS
     Lions
    1.57
     Tigers
    1.06
     lions
    0.93
     Pistons
    0.91
     Clubs
    0.89
     Blazers
    0.88
     Wolves
    0.86
     Packers
    0.86
     Bears
    0.84
     Beasts
    0.82
    Activations Density 0.004%

    No Known Activations