© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 18596
    Prev
    Next
    INDEX
    Explanations

    sports-related phrases and terms combined with words related to success or achievement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports events and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.85
     Apprentice
    -0.75
     endorsement
    -0.71
     unemploy
    -0.71
     membership
    -0.70
     internship
    -0.70
     Lifetime
    -0.69
    Posts
    -0.69
    achelor
    -0.68
    azine
    -0.67
    POSITIVE LOGITS
     halftime
    1.10
     defensively
    1.09
     turnovers
    1.05
     offensively
    1.02
     sloppy
    0.94
     midfield
    0.91
     tempo
    0.87
     rallied
    0.85
     pressuring
    0.84
     defending
    0.84
    Activations Density 0.331%

    No Known Activations