© 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. 2-RES-JB
    11. 21207
    Prev
    Next
    INDEX
    Explanations

    the word "Hay" occurring frequently

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Hay

    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
    urally
    -0.85
    ortium
    -0.82
    andestine
    -0.77
    inyl
    -0.76
     plun
    -0.74
     certific
    -0.72
     CLSID
    -0.72
     voc
    -0.71
    wcs
    -0.70
    ãĥ¯
    -0.70
    POSITIVE LOGITS
    stack
    0.97
    leigh
    0.94
     Hay
    0.94
    wire
    0.93
    bons
    0.90
    nes
    0.89
    Hay
    0.86
    ley
    0.86
    ashi
    0.85
    abus
    0.84
    Activations Density 0.005%

    No Known Activations