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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7389
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ye" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "ye" 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
     abusive
    -0.66
     economical
    -0.63
     sized
    -0.63
     associated
    -0.62
     average
    -0.61
     Marc
    -0.61
     Extended
    -0.60
     linear
    -0.60
     providers
    -0.60
     abusers
    -0.59
    POSITIVE LOGITS
    ye
    4.64
    YE
    1.98
    yes
    1.91
    yi
    1.57
    yah
    1.47
    yo
    1.45
    ya
    1.43
     Ye
    1.40
    Ye
    1.37
    aye
    1.33
    Activations Density 0.005%

    No Known Activations