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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RES-JB
    6. 11863
    Prev
    Next
    INDEX
    Explanations

    words related to religious figures or titles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of religious prophets, particularly Muhammad

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egal
    -0.78
    dit
    -0.77
    anke
    -0.74
    tten
    -0.74
    emetery
    -0.70
     rink
    -0.70
    lasses
    -0.67
     Torn
    -0.67
    wig
    -0.66
    YC
    -0.65
    POSITIVE LOGITS
     Muhammad
    1.07
    hammad
    1.04
    thood
    0.89
     Quran
    0.88
     Isaiah
    0.88
     Prophet
    0.85
    seed
    0.80
     Ø
    0.80
     Mohammed
    0.79
    ciating
    0.77
    Activations Density 0.026%

    No Known Activations