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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 19862
    Prev
    Next
    INDEX
    Explanations

    mentions of secretive or mysterious organizations, specifically "Skull & Bones"

    oai_token-act-pair · gpt-3.5-turbo

    references to secret societies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phrine
    -0.80
    rolet
    -0.76
     mosqu
    -0.72
    aila
    -0.71
    sylv
    -0.69
    lease
    -0.67
    peria
    -0.67
    ogene
    -0.67
    sburgh
    -0.66
     Lyft
    -0.66
    POSITIVE LOGITS
     Skull
    0.80
     drip
    0.79
    ĸļ
    0.64
    VERTISEMENT
    0.62
     rubbed
    0.62
     gag
    0.61
     Torch
    0.60
    ascript
    0.59
     Survivor
    0.59
     heel
    0.58
    Activations Density 0.000%

    No Known Activations