© 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. 3-RES-JB
    11. 4699
    Prev
    Next
    INDEX
    Explanations

    names or terms related to individuals named "Kendall."

    oai_token-act-pair · gpt-3.5-turbo

    names, particularly those related to individuals and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    autical
    -0.84
    anyahu
    -0.82
    latable
    -0.76
    eree
    -0.74
    untled
    -0.73
    ÃĥÃĤ
    -0.72
    IBLE
    -0.72
    odcast
    -0.72
    mingham
    -0.70
    ervative
    -0.70
    POSITIVE LOGITS
     Kush
    0.93
     Kendall
    0.89
    hyde
    0.81
    lar
    0.74
    need
    0.74
     Jenner
    0.73
    Green
    0.71
     Lamar
    0.71
     Polk
    0.69
     Kor
    0.69
    Activations Density 0.013%

    No Known Activations