© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 12777
    Prev
    Next
    INDEX
    Explanations

    terms related to fantasy role-playing games, specifically referencing dungeons

    oai_token-act-pair · gpt-3.5-turbo

    references to the game Dungeons and Dragons or similar dungeon-themed content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FTA
    -0.68
    ï¸
    -0.67
    henko
    -0.63
    vant
    -0.63
    racted
    -0.61
     optic
    -0.60
    nah
    -0.60
    chell
    -0.60
    onica
    -0.60
    hovah
    -0.60
    POSITIVE LOGITS
     Dungeon
    0.92
    geons
    0.90
     dungeons
    0.89
     crawl
    0.88
     craw
    0.87
    Leaks
    0.86
     crawling
    0.84
    geon
    0.82
     Dungeons
    0.82
     dungeon
    0.80
    Activations Density 0.007%

    No Known Activations