© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11747
    Prev
    Next
    INDEX
    Explanations

    instances where waiting is involved

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express anticipation or expectation of actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.80
     deficits
    -0.69
     overriding
    -0.64
     Controlled
    -0.63
    holding
    -0.63
     unchanged
    -0.63
     millenn
    -0.62
     dependence
    -0.62
     lacking
    -0.61
     contradiction
    -0.59
    POSITIVE LOGITS
     announce
    1.17
     unleash
    1.17
     congratulate
    1.12
     capitalize
    1.11
     celebrate
    1.11
     get
    1.09
     speak
    1.09
     join
    1.08
     begin
    1.08
     settle
    1.07
    Activations Density 0.097%

    No Known Activations