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. 3-RES-JB
    6. 10539
    Prev
    Next
    INDEX
    Explanations

    the phrase "not sure" in text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assic
    -0.73
    iang
    -0.72
    azar
    -0.70
    elin
    -0.70
    ptin
    -0.69
    ioxide
    -0.69
    rahim
    -0.68
    pez
    -0.68
    itton
    -0.68
     largeDownload
    -0.68
    POSITIVE LOGITS
     anymore
    1.73
     nor
    1.38
     anywhere
    1.00
     necessarily
    0.98
     slightest
    0.97
     whatsoever
    0.96
     anything
    0.93
     any
    0.89
     yet
    0.87
     anybody
    0.86
    Activations Density 0.290%

    No Known Activations