© 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. 0-RES-JB
    11. 10020
    Prev
    Next
    INDEX
    Explanations

    terms related to names or entities, potentially in the context of a specific organization or project

    oai_token-act-pair · gpt-3.5-turbo

    specific names or terms related to organizations and prominent figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ears
    -0.92
    istle
    -0.78
     Warehouse
    -0.71
    urb
    -0.69
    audi
    -0.67
     Resist
    -0.66
     rum
    -0.66
    ress
    -0.65
     Aston
    -0.65
    antes
    -0.64
    POSITIVE LOGITS
     Kou
    1.87
     Kra
    1.83
     KDE
    1.82
     Kau
    1.77
     Kol
    1.76
     Kle
    1.75
     Kop
    1.74
     K
    1.73
    K
    1.72
     KP
    1.70
    Activations Density 0.059%

    No Known Activations