© 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. 7458
    Prev
    Next
    INDEX
    Explanations

    references to video games

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "Games"

    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
     politic
    -0.81
    sie
    -0.75
    aye
    -0.73
    ALLY
    -0.69
     acknow
    -0.69
    gencies
    -0.68
    itudinal
    -0.63
    atever
    -0.61
     annex
    -0.61
     tow
    -0.60
    POSITIVE LOGITS
    manship
    1.20
    erver
    1.01
    paces
    0.97
     consoles
    0.90
    pace
    0.89
    OTA
    0.88
    hare
    0.85
    chool
    0.84
    pad
    0.83
    hops
    0.80
    Activations Density 0.033%

    No Known Activations