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. 0-RES-JB
    6. 289
    Prev
    Next
    INDEX
    Explanations

    the name "Sylvester" mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "vest" in various contexts

    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
     calm
    -0.66
     acid
    -0.65
     doom
    -0.61
     opponents
    -0.61
     crabs
    -0.60
     reasons
    -0.60
     plane
    -0.60
     planes
    -0.60
     answers
    -0.60
     tone
    -0.59
    POSITIVE LOGITS
    vest
    4.80
     vest
    1.36
     Vest
    1.29
    ved
    1.19
    ves
    1.14
    vard
    1.14
    vey
    1.14
    vana
    1.13
    vent
    1.09
    vell
    1.06
    Activations Density 0.013%

    No Known Activations