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. 6-RES-JB
    6. 4782
    Prev
    Next
    INDEX
    Explanations

    descriptions and discussions related to American football offensive lines

    oai_token-act-pair · gpt-3.5-turbo

    references to offensive lines in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assetsadobe
    -0.74
    £ı
    -0.74
     Taste
    -0.72
     Seller
    -0.68
    ifa
    -0.65
    eday
    -0.63
     Feminist
    -0.62
    sonian
    -0.61
     Hubble
    -0.60
    iji
    -0.60
    POSITIVE LOGITS
     mates
    0.91
     duo
    0.89
     coach
    0.88
    tackle
    0.84
     rotation
    0.83
     coaches
    0.82
     trio
    0.80
    strength
    0.80
     mate
    0.78
    leaders
    0.78
    Activations Density 0.068%

    No Known Activations