© 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. 2-RES-JB
    11. 13906
    Prev
    Next
    INDEX
    Explanations

    references to secretive or mysterious organizations or concepts, such as occult, Illuminati, esoteric, and Masonic

    oai_token-act-pair · gpt-3.5-turbo

    references to the occult, secret societies, and esoteric traditions

    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
    upon
    -0.78
    Malley
    -0.77
    BuyableInstoreAndOnline
    -0.77
    Benz
    -0.77
    Newsletter
    -0.74
    SG
    -0.74
    Wil
    -0.74
    DS
    -0.72
    Kay
    -0.72
    IRD
    -0.72
    POSITIVE LOGITS
     symbolism
    1.11
     rites
    1.08
     ritual
    0.94
     initiation
    0.93
     rituals
    0.92
     rune
    0.85
     ceremonies
    0.84
     Ritual
    0.84
     rite
    0.82
    ophical
    0.82
    Activations Density 0.034%

    No Known Activations