© 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. 1-RES-JB
    11. 613
    Prev
    Next
    INDEX
    Explanations

    mentions of "Dark" in various contexts, potentially related to titles of movies or games

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Dark" series of media, particularly in titles and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olulu
    -0.89
    oples
    -0.85
    udence
    -0.82
    neapolis
    -0.81
    ILA
    -0.81
     practiced
    -0.81
    verett
    -0.78
    awaru
    -0.77
    odcast
    -0.76
    atche
    -0.76
    POSITIVE LOGITS
    Dark
    1.07
     Dark
    1.03
    dark
    1.00
    moon
    0.92
    crow
    0.87
    grey
    0.87
    ened
    0.84
    light
    0.83
    haired
    0.82
     Horse
    0.82
    Activations Density 0.006%

    No Known Activations