© 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. 4-RES-JB
    11. 24476
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "gamer"

    oai_token-act-pair · gpt-3.5-turbo

    references to gaming culture and the identity of gamers

    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
     resusc
    -0.69
     veiled
    -0.68
    BuyableInstoreAndOnline
    -0.65
    taining
    -0.63
    eous
    -0.62
     Manson
    -0.60
     dispens
    -0.59
     crem
    -0.59
     McDonnell
    -0.58
     politic
    -0.58
    POSITIVE LOGITS
     gamers
    0.92
    boys
    0.91
    ghazi
    0.89
     gamer
    0.84
    gamer
    0.82
    haw
    0.81
    endez
    0.81
     Skydragon
    0.80
    Gam
    0.79
    gate
    0.78
    Activations Density 0.019%

    No Known Activations