© 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. 4-RES-JB
    11. 14558
    Prev
    Next
    INDEX
    Explanations

    proper names related to Christian religion

    oai_token-act-pair · gpt-3.5-turbo

    mentions of religious figures, specifically Christ and Jesus

    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
     Luxem
    -0.70
    ACP
    -0.69
    Ùĩ
    -0.69
    PRES
    -0.68
    realDonaldTrump
    -0.68
    present
    -0.67
    DragonMagazine
    -0.66
    ODUCT
    -0.65
    CLASS
    -0.65
    EGIN
    -0.62
    POSITIVE LOGITS
    ophe
    0.74
    zyk
    0.72
    atta
    0.71
    ode
    0.69
    ayne
    0.69
    hurst
    0.66
    ja
    0.63
    ega
    0.62
    sey
    0.62
     wraps
    0.61
    Activations Density 0.062%

    No Known Activations