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. 16489
    Prev
    Next
    INDEX
    Explanations

    information related to sports, including player signings, game statistics, team updates, and player performance

    oai_token-act-pair · gpt-3.5-turbo

    the end of the text passage

    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
     ®
    -0.70
    orno
    -0.64
     Feminist
    -0.61
    bara
    -0.55
     foc
    -0.55
     jew
    -0.54
     anten
    -0.53
     civilisation
    -0.53
    microsoft
    -0.53
     000
    -0.52
    POSITIVE LOGITS
     offseason
    0.95
     rookie
    0.93
     postseason
    0.92
     preseason
    0.91
     ESPN
    0.90
    ESPN
    0.90
     Rookie
    0.90
     undrafted
    0.87
    juries
    0.87
    NFL
    0.87
    Activations Density 1.492%

    No Known Activations