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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 17412
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and competitions, specifically football

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports eligibility and injuries

    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
     ®
    -0.82
     UNESCO
    -0.69
     photoc
    -0.67
    CHQ
    -0.66
     +---
    -0.65
    )",
    -0.64
     NGOs
    -0.62
     paed
    -0.61
     leaflets
    -0.60
     programmes
    -0.60
    POSITIVE LOGITS
     offseason
    1.18
     preseason
    1.09
    juries
    1.09
     undrafted
    1.02
     rookie
    1.01
     Rookie
    1.01
     rookies
    0.98
     playoff
    0.97
    NFL
    0.96
     matchup
    0.96
    Activations Density 2.240%

    No Known Activations