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. 2460
    Prev
    Next
    INDEX
    Explanations

    words related to football programs or teams

    oai_token-act-pair · gpt-3.5-turbo

    references to specific college football programs and teams

    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
    block
    -0.74
     compartment
    -0.72
    orders
    -0.68
     drip
    -0.67
     VAT
    -0.67
     ponies
    -0.66
     Panzer
    -0.64
    mentioned
    -0.64
     orders
    -0.63
     authorised
    -0.63
    POSITIVE LOGITS
     Athletic
    1.11
     Athletics
    1.11
     athletics
    1.05
     athletic
    0.97
     alum
    0.95
    keyes
    0.95
     Bulldogs
    0.91
     University
    0.88
     Wildcats
    0.87
     Bears
    0.86
    Activations Density 0.152%

    No Known Activations