© 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. 7-RES-JB
    11. 1545
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or indecision

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing confusion or uncertainty about actions or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urance
    -0.62
    members
    -0.61
    quad
    -0.60
     Confeder
    -0.58
     Vox
    -0.57
    artisan
    -0.57
    ĸļ
    -0.57
     vouchers
    -0.57
     Nurs
    -0.57
    creator
    -0.56
    POSITIVE LOGITS
     eat
    1.01
     choose
    0.95
     give
    0.94
     take
    0.94
     characterize
    0.93
     interpret
    0.92
     classify
    0.92
     blame
    0.92
     inflict
    0.92
     expect
    0.90
    Activations Density 0.066%

    No Known Activations