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. 20879
    Prev
    Next
    INDEX
    Explanations

    words related to trading or bartering

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "trade."

    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
     ye
    -0.62
     cause
    -0.60
     rehe
    -0.60
     Sym
    -0.58
     yeast
    -0.58
     composition
    -0.57
     phon
    -0.57
     Whe
    -0.57
     recoil
    -0.57
     ident
    -0.56
    POSITIVE LOGITS
    aded
    4.41
    ading
    2.77
    ades
    2.54
    ade
    2.01
    aders
    1.98
    ADE
    1.97
    ader
    1.59
    asion
    1.54
    asive
    1.39
    eded
    1.17
    Activations Density 0.007%

    No Known Activations