© 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. 10400
    Prev
    Next
    INDEX
    Explanations

    words related to sports statistics, particularly focusing on the performance of athletes in games

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "allowed" and related context in sports statistics

    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
    enegger
    -1.01
    sonian
    -0.77
     concess
    -0.76
    idi
    -0.73
    clus
    -0.72
     welf
    -0.71
    aida
    -0.67
    col
    -0.67
    aim
    -0.66
     anat
    -0.66
    POSITIVE LOGITS
    Defense
    0.85
     opponents
    0.82
     touchdowns
    0.79
     defenses
    0.78
     turnovers
    0.77
     rookies
    0.76
     conceded
    0.75
    ÙĴ
    0.75
     rookie
    0.74
     playoff
    0.74
    Activations Density 0.047%

    No Known Activations