© 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. 8-RES-JB
    11. 2474
    Prev
    Next
    INDEX
    Explanations

    the name "Ernie" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    names of people, specifically those with the suffix 'nie'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iance
    -1.09
    yrus
    -0.94
    ily
    -0.92
    iar
    -0.87
    inas
    -0.84
    inis
    -0.84
    ijk
    -0.79
    inion
    -0.79
    ragon
    -0.78
    liner
    -0.78
    POSITIVE LOGITS
     Mae
    0.98
     Yen
    0.86
     Mouse
    0.85
    IELD
    0.77
     Ig
    0.76
    ãĤ¡
    0.74
     Barcl
    0.71
     Lenn
    0.71
     Kem
    0.71
     Ago
    0.71
    Activations Density 0.089%

    No Known Activations