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. 9862
    Prev
    Next
    INDEX
    Explanations

    references to a person named "Jake"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Jake."

    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
     subst
    -0.69
     circ
    -0.66
    iary
    -0.65
     systematic
    -0.65
    inances
    -0.65
    election
    -0.64
    perse
    -0.64
     periphery
    -0.62
     conduc
    -0.62
    sound
    -0.62
    POSITIVE LOGITS
     Jake
    1.31
    Jake
    1.07
    glers
    0.95
     Skywalker
    0.87
     Abrams
    0.85
    imaru
    0.84
     Roberts
    0.80
    JJ
    0.80
     Foley
    0.79
     Sullivan
    0.79
    Activations Density 0.004%

    No Known Activations