© 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. 5285
    Prev
    Next
    INDEX
    Explanations

    names, particularly "Clayton" and "Clarence"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Clayton."

    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
    natureconservancy
    -0.99
    ku
    -0.94
    ebook
    -0.80
    ãĤ£
    -0.79
    ============
    -0.78
    ãĥ´ãĤ¡
    -0.78
    rolog
    -0.78
    system
    -0.75
    atable
    -0.74
    ========
    -0.74
    POSITIVE LOGITS
     Clayton
    1.13
     Kers
    1.09
     Mills
    0.81
     Christensen
    0.79
     Keller
    0.71
    xus
    0.71
    oqu
    0.71
     Porter
    0.70
    ylon
    0.69
    imore
    0.67
    Activations Density 0.017%

    No Known Activations