© 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. 9-RES-JB
    11. 15487
    Prev
    Next
    INDEX
    Explanations

    the phrase "not sure."

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĥİ
    -0.78
    emonium
    -0.77
    verse
    -0.75
    inator
    -0.67
    %]
    -0.65
    cano
    -0.65
    ufact
    -0.63
    inators
    -0.63
    ulus
    -0.61
    gencies
    -0.61
    POSITIVE LOGITS
     why
    1.11
     whether
    1.10
     how
    1.10
     about
    0.91
     if
    0.90
     exactly
    0.87
     WHY
    0.87
    why
    0.84
     what
    0.82
     anymore
    0.74
    Activations Density 0.045%

    No Known Activations