© 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. 1-RES-JB
    11. 362
    Prev
    Next
    INDEX
    Explanations

    sentences containing the word "unclear"

    oai_token-act-pair · gpt-3.5-turbo

    instances of uncertainty or lack of clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocard
    -0.75
    OF
    -0.72
    rera
    -0.71
    gall
    -0.71
    endar
    -0.70
    INT
    -0.69
    anders
    -0.69
    glas
    -0.67
    ogie
    -0.66
    ingo
    -0.66
    POSITIVE LOGITS
     unclear
    0.77
    comings
    0.76
    wcs
    0.76
     unlaw
    0.69
    entimes
    0.68
     ambiguous
    0.67
    icably
    0.66
     conflicting
    0.66
     NEC
    0.65
     derailed
    0.65
    Activations Density 0.007%

    No Known Activations