© 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. 11-RES-JB
    11. 9322
    Prev
    Next
    INDEX
    Explanations

    positive and negative descriptions of performance in baseball

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of player performance metrics in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÅŁ
    -0.92
    ë
    -0.84
     Euph
    -0.81
     Pai
    -0.80
    Sham
    -0.80
    ê
    -0.77
     Vive
    -0.76
    Syrian
    -0.76
    ç
    -0.76
     Chao
    -0.75
    POSITIVE LOGITS
     RBI
    1.56
     shortstop
    1.56
     batted
    1.55
     batting
    1.51
     hitter
    1.49
     homers
    1.45
     outfielder
    1.44
     outfield
    1.44
     Cabrera
    1.40
     slug
    1.40
    Activations Density 0.214%

    No Known Activations