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. 3186
    Prev
    Next
    INDEX
    Explanations

    proper names related to sports

    oai_token-act-pair · gpt-3.5-turbo

    references to the basketball player Giannis Antetokounmpo and terms related to improvement or enhancement

    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
    azo
    -0.74
    lda
    -0.73
    OPLE
    -0.69
     Laden
    -0.68
     Kimber
    -0.67
    ĸļ
    -0.64
     Blaze
    -0.63
    aminer
    -0.61
    hyde
    -0.61
    PLA
    -0.61
    POSITIVE LOGITS
    acies
    1.00
    viation
    0.87
    bling
    0.84
    saf
    0.83
    safe
    0.82
    ses
    0.80
    haw
    0.79
    s
    0.79
    pre
    0.78
    bly
    0.76
    Activations Density 0.065%

    No Known Activations