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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20
    Prev
    Next
    INDEX
    Explanations

    mentions of religious groups, particularly Christians, in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Christians and Christianity

    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
    daq
    -0.67
     Poké
    -0.65
     blade
    -0.64
     storage
    -0.64
     IG
    -0.62
     controller
    -0.62
     retri
    -0.62
    pocket
    -0.62
     interface
    -0.62
     operator
    -0.61
    POSITIVE LOGITS
     Christians
    3.63
     Christianity
    2.41
     Catholics
    2.37
     Protestants
    2.32
     atheists
    2.20
     evangelicals
    2.19
     Christian
    2.19
    Christian
    2.05
     Muslims
    2.01
     Hindus
    2.00
    Activations Density 0.017%

    No Known Activations