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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14803
    Prev
    Next
    INDEX
    Explanations

    descriptions related to baseball actions and statistics

    oai_token-act-pair · gpt-3.5-turbo

    key metrics and statistics related to sports performance

    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
    -0.80
    opian
    -0.74
    DragonMagazine
    -0.73
    grim
    -0.71
    sonian
    -0.69
    Virgin
    -0.67
    Priv
    -0.66
     organising
    -0.66
     accredited
    -0.66
     MFT
    -0.66
    POSITIVE LOGITS
     batted
    0.90
     reliever
    0.84
     linem
    0.81
    querque
    0.80
     hitter
    0.80
     RBI
    0.78
     tallied
    0.75
     catcher
    0.75
     hitters
    0.74
     bullpen
    0.74
    Activations Density 0.166%

    No Known Activations