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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-RES-JB
    6. 6043
    Prev
    Next
    INDEX
    Explanations

    mentions of atheism or atheists

    oai_token-act-pair · gpt-3.5-turbo

    references to atheism and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lans
    -0.82
    ior
    -0.72
     Lakes
    -0.72
     Canal
    -0.66
    drops
    -0.65
    OVER
    -0.64
    WIND
    -0.63
    ription
    -0.63
    lines
    -0.62
     Aden
    -0.61
    POSITIVE LOGITS
     laureate
    0.83
    ħĭ
    0.76
     creed
    0.74
    hemy
    0.72
     bigot
    0.72
    bel
    0.70
     atheist
    0.68
     detector
    0.67
     dogma
    0.67
     manifesto
    0.66
    Activations Density 0.035%

    No Known Activations