© 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. 13843
    Prev
    Next
    INDEX
    Explanations

    numerical figures or statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to numerical figures and statistical data

    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
    ovie
    -0.70
    Interstitial
    -0.68
     ENG
    -0.67
     RNA
    -0.64
     rud
    -0.64
    NetMessage
    -0.62
     Brilliant
    -0.60
    Pros
    -0.60
    ologue
    -0.60
     Recipes
    -0.59
    POSITIVE LOGITS
     fluct
    1.21
     exceeds
    1.21
     rises
    1.14
     exceeded
    1.09
     climbs
    1.08
     estimates
    1.07
     dwar
    1.06
     varies
    1.05
     dwind
    1.03
     estimate
    1.03
    Activations Density 0.210%

    No Known Activations