© 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. 6-RES-JB
    11. 13687
    Prev
    Next
    INDEX
    Explanations

    words related to sports events, particularly finals and championships

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Final" or variations thereof, indicating championship events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    relative
    -0.74
    maid
    -0.68
    behavior
    -0.67
    spr
    -0.67
    urat
    -0.66
    limit
    -0.65
    beh
    -0.65
    raved
    -0.63
    afort
    -0.63
    Sov
    -0.62
    POSITIVE LOGITS
    ists
    0.98
    isers
    0.90
    izers
    0.89
    ist
    0.84
     FANTASY
    0.84
    izes
    0.84
    izer
    0.82
    izing
    0.81
     Fantasy
    0.79
    aneously
    0.77
    Activations Density 0.018%

    No Known Activations