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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 15069
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jamie"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Jamie" and its connection to JPMorgan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.86
    esan
    -0.85
    yp
    -0.77
    ocrine
    -0.74
    orative
    -0.73
    agonist
    -0.72
    recomm
    -0.72
    agonists
    -0.71
    ICAL
    -0.70
    itarian
    -0.68
    POSITIVE LOGITS
     Oliver
    0.86
     Jamie
    0.85
    Jamie
    0.80
    ¶ħ
    0.74
     Dim
    0.71
     Herrera
    0.68
     nodd
    0.67
    ricanes
    0.65
    hawk
    0.64
    ftime
    0.64
    Activations Density 0.005%

    No Known Activations