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

    Neuronpedia

    Jacobian LensNEW
    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. 7311
    Prev
    Next
    INDEX
    Explanations

    phrases related to churches

    oai_token-act-pair · gpt-3.5-turbo

    references to church and religious institutions

    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
    Accessory
    -0.74
    à¸
    -0.72
    DonaldTrump
    -0.71
    LER
    -0.69
     Yak
    -0.64
    lasses
    -0.63
    TRUMP
    -0.63
     "$:/
    -0.62
    gets
    -0.61
    ãģ¦
    -0.61
    POSITIVE LOGITS
    goers
    1.11
    esan
    0.92
     choir
    0.92
    church
    0.91
    yard
    0.90
     fathers
    0.86
     hierarchy
    0.86
     cha
    0.83
     church
    0.83
     churches
    0.83
    Activations Density 0.016%

    No Known Activations