© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 18867
    Prev
    Next
    INDEX
    Explanations

    sentences starting with the word "Note," possibly indicating important points or comments

    oai_token-act-pair · gpt-3.5-turbo

    sections of text labeled or indicated by "Note."

    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
    nels
    -0.77
     reinvent
    -0.67
    usters
    -0.62
     crowds
    -0.62
     wre
    -0.62
    atics
    -0.60
     lay
    -0.59
     organised
    -0.58
     governed
    -0.58
    naires
    -0.58
    POSITIVE LOGITS
     Note
    3.71
     note
    2.43
     NOTE
    2.41
    Note
    2.30
    note
    2.17
     Notes
    2.01
     Notice
    1.94
    Notice
    1.52
    NOTE
    1.52
    Notes
    1.43
    Activations Density 0.016%

    No Known Activations