Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 17485
    Prev
    Next
    INDEX
    Explanations

    the name "Christ" or any variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Christ" and its variations

    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
     Pocket
    -0.74
     fly
    -0.72
     Fly
    -0.71
     flair
    -0.71
     digest
    -0.69
     Melee
    -0.68
     Slime
    -0.68
     UA
    -0.66
     RNA
    -0.65
     Mega
    -0.64
    POSITIVE LOGITS
    Christ
    3.99
    christ
    2.32
     CHRIST
    1.93
    Christian
    1.86
     Christ
    1.64
     christ
    1.58
    Jesus
    1.57
     Christie
    1.52
    Cath
    1.49
     Christians
    1.47
    Activations Density 0.020%

    No Known Activations