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. 7175
    Prev
    Next
    INDEX
    Explanations

    words related to parting or bidding farewell

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to saying goodbye or farewells

    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
    mental
    -0.66
     infl
    -0.62
     tri
    -0.61
    icals
    -0.59
     identified
    -0.58
    ason
    -0.58
    ams
    -0.58
     cited
    -0.57
     Democr
    -0.57
     Frames
    -0.57
    POSITIVE LOGITS
     goodbye
    4.66
     farewell
    3.26
     Goodbye
    2.59
     hello
    2.08
    bye
    1.75
     parting
    1.55
     bye
    1.54
    hello
    1.37
     Bye
    1.27
     congratulations
    1.19
    Activations Density 0.014%

    No Known Activations