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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 23766
    Prev
    Next
    INDEX
    Explanations

    numerical values related to statistics in sports

    oai_token-act-pair · gpt-3.5-turbo

    numerical statistics related to sports performance

    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
    folk
    -0.68
    ilic
    -0.61
    evin
    -0.60
    produced
    -0.57
    claimer
    -0.56
     parted
    -0.56
    Thumbnail
    -0.56
    atham
    -0.55
    aucuses
    -0.54
    ifice
    -0.54
    POSITIVE LOGITS
    aciously
    0.98
     consecutive
    0.97
     percent
    0.83
    ½
    0.82
     million
    0.80
     watts
    0.78
     kilograms
    0.77
     minutes
    0.76
     trillion
    0.75
     ounces
    0.74
    Activations Density 0.228%

    No Known Activations