Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 592
    Prev
    Next
    INDEX
    Explanations

    the name "Nathan"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Nathan" in the text

    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
    awaru
    -0.72
    omething
    -0.71
    rera
    -0.69
    hops
    -0.68
    acies
    -0.68
    ebook
    -0.67
    å§«
    -0.67
     corrid
    -0.65
    essee
    -0.64
    20439
    -0.64
    POSITIVE LOGITS
     Nathan
    1.00
    elson
    0.97
     Hale
    0.96
     Rothschild
    0.80
     Mayer
    0.80
    athan
    0.79
     Bedford
    0.78
     Grayson
    0.78
    elsen
    0.77
     Bee
    0.74
    Activations Density 0.007%

    No Known Activations