© 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. 8-RES-JB
    11. 1069
    Prev
    Next
    INDEX
    Explanations

    words related to delays, overruns, and work

    oai_token-act-pair · gpt-3.5-turbo

    instances of delays, discrepancies, and patterns in processes or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ital
    -0.69
    ghazi
    -0.67
     Saying
    -0.64
     anyways
    -0.64
    $.
    -0.63
    cise
    -0.63
    avis
    -0.61
    CI
    -0.58
    esson
    -0.57
     Funny
    -0.57
    POSITIVE LOGITS
     exists
    1.41
     emerges
    1.37
     ensued
    1.37
     emerged
    1.33
     awaits
    1.31
     existed
    1.22
     prevailed
    1.20
     arose
    1.20
     occurred
    1.12
     arises
    1.10
    Activations Density 0.577%

    No Known Activations