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. 11-RES-JB
    6. 19853
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to uncertainty or contemplation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating uncertainty or subjective opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icipated
    -0.86
     awaited
    -0.77
     pending
    -0.75
     completed
    -0.70
     confir
    -0.69
     renewed
    -0.66
     finalized
    -0.65
     awaiting
    -0.65
     ensured
    -0.65
     arri
    -0.63
    POSITIVE LOGITS
    People
    1.03
    Everybody
    1.02
    They
    0.98
    Yeah
    0.98
    laughs
    0.95
     Everybody
    0.94
    Nobody
    0.94
    nob
    0.90
    Sometimes
    0.89
     Somebody
    0.89
    Activations Density 0.436%

    No Known Activations