© 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. 0-RES-JB
    11. 9399
    Prev
    Next
    INDEX
    Explanations

    names related to the name "James"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "James."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tag
    -0.80
     trough
    -0.78
     (%
    -0.74
     monop
    -0.70
    UI
    -0.69
    otin
    -0.68
    tl
    -0.67
     resil
    -0.67
     Drupal
    -0.66
    Chain
    -0.66
    POSITIVE LOGITS
     James
    3.34
    James
    2.89
     Jim
    1.49
     Thomas
    1.48
     Benjamin
    1.46
     Charles
    1.45
     Andrew
    1.43
     John
    1.41
     Daniel
    1.40
     Anthony
    1.40
    Activations Density 0.024%

    No Known Activations