© 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. 17193
    Prev
    Next
    INDEX
    Explanations

    words related to the sport baseball

    oai_token-act-pair · gpt-3.5-turbo

    references to baseball

    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
     Ples
    -0.89
     Beir
    -0.78
    vo
    -0.76
    ablishment
    -0.74
    ages
    -0.72
    ims
    -0.72
    adow
    -0.72
    tern
    -0.72
     McKenna
    -0.71
    eely
    -0.70
    POSITIVE LOGITS
     baseball
    0.98
     Baseball
    0.94
     batting
    0.82
     pitcher
    0.82
     batted
    0.81
     stadiums
    0.81
     pitchers
    0.81
    BIP
    0.79
    BALL
    0.79
     glove
    0.78
    Activations Density 0.010%

    No Known Activations