© 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. 10-RES-JB
    11. 16687
    Prev
    Next
    INDEX
    Explanations

    questions or uncertainties about what action to take

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing uncertainty or confusion about actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quad
    -0.65
    aires
    -0.64
    panel
    -0.64
    members
    -0.62
    ĵ
    -0.61
    ģĸ
    -0.61
     proving
    -0.60
     vanquished
    -0.59
     validated
    -0.59
    ¹
    -0.59
    POSITIVE LOGITS
     expect
    1.28
    ilers
    0.89
     classify
    0.89
    igl
    0.88
     prioritize
    0.87
     say
    0.86
     believe
    0.84
     eat
    0.84
     Expect
    0.84
     buy
    0.83
    Activations Density 0.042%

    No Known Activations