© 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. 8-RES-JB
    11. 17685
    Prev
    Next
    INDEX
    Explanations

    boss fights, boss characters, and levels in video games

    oai_token-act-pair · gpt-3.5-turbo

    references to boss encounters and level designs in video games

    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
     Marketable
    -0.71
    ufact
    -0.69
    maid
    -0.67
    ignt
    -0.66
    phil
    -0.66
    isma
    -0.66
    riger
    -0.65
     cellul
    -0.65
    chuk
    -0.64
    audi
    -0.63
    POSITIVE LOGITS
     dungeons
    1.09
     playthrough
    1.06
     puzzles
    1.05
     dungeon
    1.03
     craw
    1.02
     respawn
    0.99
     crawl
    0.97
     crawling
    0.97
     gameplay
    0.97
     proced
    0.96
    Activations Density 0.240%

    No Known Activations