© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6936
    Prev
    Next
    INDEX
    Explanations

    words related to dungeons and gaming terminology

    oai_token-act-pair · gpt-3.5-turbo

    references to dungeons and related fantasy gaming concepts

    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
    ï¸
    -0.76
     FTA
    -0.76
    LM
    -0.67
    henko
    -0.67
     antioxid
    -0.66
    ivities
    -0.66
    resent
    -0.64
    ciation
    -0.64
     Aad
    -0.64
    vant
    -0.63
    POSITIVE LOGITS
     crawl
    0.95
     crawling
    0.92
    geons
    0.91
     dungeons
    0.86
     craw
    0.86
    Leaks
    0.86
     dungeon
    0.83
    naires
    0.80
    geon
    0.77
     Fighter
    0.76
    Activations Density 0.016%

    No Known Activations