© 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. 2-RES-JB
    11. 6291
    Prev
    Next
    INDEX
    Explanations

    words related to bats

    oai_token-act-pair · gpt-3.5-turbo

    mentions of bats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´ãĤ¡
    -0.93
    naire
    -0.84
     Scotia
    -0.76
    CE
    -0.72
    andro
    -0.69
    nee
    -0.68
    姫
    -0.67
    abet
    -0.66
    xia
    -0.63
    IA
    -0.63
    POSITIVE LOGITS
     bats
    1.10
    bats
    1.07
    manship
    1.00
     cricket
    0.87
    balls
    0.81
     Cricket
    0.80
    men
    0.79
     batting
    0.79
     beetles
    0.79
    uit
    0.77
    Activations Density 0.007%

    No Known Activations