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. 5-RES-JB
    6. 8092
    Prev
    Next
    INDEX
    Explanations

    statistics related to sports performance

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to player performance percentages in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Asia
    -0.73
    opol
    -0.71
     privat
    -0.70
     Horizons
    -0.69
    AFTA
    -0.69
    aco
    -0.68
     Panel
    -0.67
     postp
    -0.66
     Xen
    -0.65
     ®
    -0.63
    POSITIVE LOGITS
     offensively
    0.93
    orsi
    0.87
    BIP
    0.86
     Cors
    0.81
     (.
    0.81
     fastball
    0.80
     athleticism
    0.79
    Stats
    0.78
     coefficient
    0.78
     stats
    0.77
    Activations Density 0.106%

    No Known Activations