© 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. 11187
    Prev
    Next
    INDEX
    Explanations

    words related to gaming and gamers

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gaming and gamers

    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
     Debor
    -0.68
    ioxide
    -0.63
    uilt
    -0.63
    von
    -0.62
    reek
    -0.62
     Bolton
    -0.61
    wait
    -0.61
    iffe
    -0.60
     Manson
    -0.59
     poem
    -0.59
    POSITIVE LOGITS
     consoles
    1.25
    cube
    0.98
     console
    0.96
     PCs
    0.90
    ghazi
    0.90
    intendo
    0.90
    console
    0.89
    Console
    0.87
     peripher
    0.87
    pad
    0.87
    Activations Density 0.059%

    No Known Activations