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. 2-RES-JB
    6. 9887
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific positions in American football such as "cornerback" and "shortstop"

    oai_token-act-pair · gpt-3.5-turbo

    references to football positions, particularly cornerbacks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emon
    -0.82
    ename
    -0.82
    estone
    -0.77
    emb
    -0.77
    cius
    -0.75
    ofi
    -0.75
    vg
    -0.75
    arist
    -0.73
    itia
    -0.73
    ZI
    -0.73
    POSITIVE LOGITS
     cornerback
    1.03
     linebacker
    0.74
     CB
    0.69
     outfielder
    0.68
     Franch
    0.67
     corners
    0.66
     Cary
    0.66
     infield
    0.66
     waivers
    0.65
     Arche
    0.64
    Activations Density 0.010%

    No Known Activations