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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 5424
    Prev
    Next
    INDEX
    Explanations

    uncertainty or lack of knowledge

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "I don't know."

    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
    ItemTracker
    -0.88
    conservancy
    -0.81
    isco
    -0.74
    phrine
    -0.74
    uilding
    -0.72
    asus
    -0.72
    coni
    -0.71
    resa
    -0.70
    atism
    -0.69
    utenberg
    -0.69
    POSITIVE LOGITS
    ledged
    0.93
     anymore
    0.88
     anything
    0.84
     exactly
    0.77
    lege
    0.77
     enough
    0.77
    ariat
    0.76
     how
    0.75
     yet
    0.73
    ledge
    0.71
    Activations Density 0.045%

    No Known Activations