© 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. 10-RES-JB
    11. 18715
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "wait"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wait" in various contexts

    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
     converter
    -0.68
    ãĤº
    -0.64
    reb
    -0.64
    insula
    -0.56
     conver
    -0.54
    matically
    -0.53
    eatured
    -0.52
    initions
    -0.52
    ortium
    -0.52
    ãĥģ
    -0.51
    POSITIVE LOGITS
    resses
    1.17
    rose
    1.04
    listed
    1.04
    ressing
    0.98
    staff
    0.95
    ress
    0.92
     patiently
    0.89
    wait
    0.89
    amin
    0.86
    list
    0.82
    Activations Density 0.029%

    No Known Activations