© 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. 3-RES-JB
    11. 149
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "bats" related to sports equipment or animals

    oai_token-act-pair · gpt-3.5-turbo

    references to bats in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´ãĤ¡
    -0.94
    naire
    -0.79
     Scotia
    -0.73
    ovo
    -0.72
    CE
    -0.71
    zanne
    -0.71
    ual
    -0.66
    xia
    -0.65
    via
    -0.65
    uthor
    -0.64
    POSITIVE LOGITS
    manship
    1.14
     bats
    1.04
    bats
    0.92
     cricket
    0.89
    man
    0.84
    men
    0.81
    bane
    0.81
    woman
    0.80
     batting
    0.79
     Cricket
    0.78
    Activations Density 0.004%

    No Known Activations