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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 5723
    Prev
    Next
    INDEX
    Explanations

    mentions of football positions, particularly the quarterback

    oai_token-act-pair · gpt-3.5-turbo

    references to the quarterback position in football

    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
    ktop
    -0.82
    ename
    -0.71
    atom
    -0.68
    service
    -0.68
    henko
    -0.68
     ns
    -0.66
    nz
    -0.66
    issan
    -0.65
    enta
    -0.65
    rip
    -0.63
    POSITIVE LOGITS
     coach
    0.93
     quarterback
    0.85
     QB
    0.81
     Peyton
    0.78
     Coach
    0.75
     guru
    0.75
     Trevor
    0.75
     whis
    0.74
    Coach
    0.72
     Manziel
    0.70
    Activations Density 0.025%

    No Known Activations