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. 15740
    Prev
    Next
    INDEX
    Explanations

    references to the sports team "New England Patriots."

    oai_token-act-pair · gpt-3.5-turbo

    references to the New England Patriots football team

    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
    lasses
    -0.85
    undai
    -0.80
    osta
    -0.74
    yrinth
    -0.73
     peas
    -0.72
    tips
    -0.72
    rowth
    -0.70
    spl
    -0.67
    orescence
    -0.67
    conservancy
    -0.67
    POSITIVE LOGITS
     Patriots
    0.99
     Chiefs
    0.75
    ichick
    0.75
     Mariners
    0.74
     Jets
    0.74
    riots
    0.73
     Belichick
    0.72
     Amend
    0.71
     Islanders
    0.70
     Bom
    0.69
    Activations Density 0.018%

    No Known Activations