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. 14543
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a comparison among different groups or categories

    oai_token-act-pair · gpt-3.5-turbo

    the repeated phrase "Among," indicating a focus on comparative or contextual references in discussions

    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
     reset
    -0.72
     otherwise
    -0.71
     closure
    -0.69
     normal
    -0.69
     fiat
    -0.65
     grid
    -0.63
     semi
    -0.62
     rubber
    -0.61
     lines
    -0.61
     press
    -0.60
    POSITIVE LOGITS
     Among
    3.46
    Among
    2.61
    among
    2.27
     among
    1.74
     Included
    1.57
     amongst
    1.49
     Notably
    1.46
     Along
    1.41
     Including
    1.32
     Across
    1.31
    Activations Density 0.014%

    No Known Activations