© 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. 11-RES-JB
    11. 7165
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the passage of time or urgency

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     testim
    -0.64
    erness
    -0.62
    STER
    -0.60
    orted
    -0.59
     KB
    -0.57
     Principles
    -0.57
    ebin
    -0.57
     STORY
    -0.57
     Rankings
    -0.56
    artisan
    -0.55
    POSITIVE LOGITS
     later
    1.63
    later
    1.37
     Later
    1.24
    Later
    1.19
     sooner
    1.11
     thereafter
    1.09
     afterwards
    1.02
     hereafter
    1.00
     subsequently
    0.99
     farther
    0.99
    Activations Density 0.057%

    No Known Activations