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. 9-RES-JB
    6. 19246
    Prev
    Next
    INDEX
    Explanations

    statistics and performance metrics related to sports

    oai_token-act-pair · gpt-3.5-turbo

    statistical details related to football player performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.71
    forums
    -0.70
    hao
    -0.68
    MQ
    -0.68
    wcsstore
    -0.65
    kens
    -0.64
    Gaming
    -0.64
    lyak
    -0.64
    conom
    -0.64
    ragon
    -0.62
    POSITIVE LOGITS
     touchdowns
    1.11
     touchdown
    1.10
     yards
    0.98
     TDs
    0.90
     rusher
    0.80
     td
    0.79
     scrimmage
    0.79
     offense
    0.76
     rushing
    0.76
     punt
    0.73
    Activations Density 0.053%

    No Known Activations