© 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. 4-RES-JB
    11. 1803
    Prev
    Next
    INDEX
    Explanations

    names or words related to the name "Sou"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sou."

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

    No Comments

    Negative Logits
     Bermuda
    -0.77
    OY
    -0.72
     Kirin
    -0.67
     Clarkson
    -0.66
    Ö¼
    -0.66
     Pax
    -0.65
    Ø©
    -0.64
     Lyme
    -0.63
     Camden
    -0.63
     birth
    -0.62
    POSITIVE LOGITS
    ven
    1.08
    reth
    1.04
    rend
    1.00
    quet
    0.99
    plet
    0.98
    hou
    0.93
    gue
    0.92
    cery
    0.92
    chet
    0.91
    lette
    0.91
    Activations Density 0.012%

    No Known Activations