Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 15747
    Prev
    Next
    INDEX
    Explanations

    sports matchups

    oai_token-act-pair · gpt-3.5-turbo

    matchup-related terms in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    minecraft
    -0.84
    forums
    -0.81
     bearings
    -0.78
     artic
    -0.71
    umatic
    -0.70
    iott
    -0.70
    Whe
    -0.70
    Animation
    -0.69
    wcs
    -0.69
    milo
    -0.68
    POSITIVE LOGITS
     RHP
    0.78
     Kansas
    0.78
     Serbia
    0.77
     Sioux
    0.77
     Petr
    0.76
     Reno
    0.74
     preseason
    0.74
     Chiefs
    0.74
     Devils
    0.74
     Ivan
    0.73
    Activations Density 0.083%

    No Known Activations