Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 5907
    Prev
    Next
    INDEX
    Explanations

    references to waiting in a physical or metaphorical line

    oai_token-act-pair · gpt-3.5-turbo

    references to queues and waiting lines

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

    No Comments

    Negative Logits
    oral
    -0.70
     mathemat
    -0.65
    inav
    -0.62
    aryl
    -0.61
     Arkham
    -0.61
    agnetic
    -0.60
    wig
    -0.60
    anthrop
    -0.59
     VIDEOS
    -0.59
     Hebrew
    -0.59
    POSITIVE LOGITS
     queue
    1.11
    Queue
    1.09
    queue
    1.02
     queues
    0.99
    erness
    0.97
    naires
    0.87
     Que
    0.85
    eers
    0.80
     que
    0.77
    naire
    0.76
    Activations Density 0.012%

    No Known Activations