© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22280
    Prev
    Next
    INDEX
    Explanations

    references to sports matches and games

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating competition or confrontations in sports contexts

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

    No Comments

    Negative Logits
    sonian
    -0.91
    zel
    -0.85
    details
    -0.84
    zl
    -0.84
    overed
    -0.82
    wcs
    -0.80
    ouf
    -0.80
    udder
    -0.78
    lus
    -0.77
    pots
    -0.76
    POSITIVE LOGITS
     opponents
    0.85
     Samoa
    0.82
     foes
    0.77
     against
    0.77
     Cortex
    0.76
     opponent
    0.74
     Nag
    0.72
     Ireland
    0.69
     Kansas
    0.69
     Blow
    0.68
    Activations Density 0.035%

    No Known Activations