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

    Neuronpedia

    Jacobian LensNEW
    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. 14673
    Prev
    Next
    INDEX
    Explanations

    mention of baseball pitchers, often with specific details such as handedness or achievements

    oai_token-act-pair · gpt-3.5-turbo

    references to baseball pitchers

    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
    busters
    -0.82
    illion
    -0.80
    zhou
    -0.76
    hent
    -0.75
    tan
    -0.73
    ives
    -0.72
    ë
    -0.72
     Lumpur
    -0.72
     Imperium
    -0.72
    riott
    -0.69
    POSITIVE LOGITS
     pitcher
    1.11
     pitchers
    1.05
     pitching
    0.95
     velocity
    0.92
     pitched
    0.88
     reliever
    0.84
     ERA
    0.82
     mound
    0.80
     catcher
    0.75
     hur
    0.74
    Activations Density 0.034%

    No Known Activations