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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 8766
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Christian" with varying levels of relevance

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Christian" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obbies
    -0.82
    ickr
    -0.76
    frames
    -0.75
    draft
    -0.75
    tub
    -0.73
    è¦ļéĨĴ
    -0.72
    ariat
    -0.71
    æ©
    -0.71
    ðĿ
    -0.71
    sharing
    -0.70
    POSITIVE LOGITS
     Christian
    0.98
     Bale
    0.92
     missionaries
    0.91
     theolog
    0.91
     Evangel
    0.85
     Christians
    0.85
     evangel
    0.82
     faiths
    0.80
     fundamentalist
    0.80
     pastor
    0.78
    Activations Density 0.007%

    No Known Activations