© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 17102
    Prev
    Next
    INDEX
    Explanations

    references to mosques

    oai_token-act-pair · gpt-3.5-turbo

    references to mosques

    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
    dit
    -0.79
    lasses
    -0.73
    gest
    -0.67
    lass
    -0.65
    xit
    -0.64
    yon
    -0.63
    eu
    -0.63
    Produ
    -0.61
    lust
    -0.61
    sum
    -0.61
    POSITIVE LOGITS
     loudspe
    1.04
     entrances
    0.82
     congregation
    0.82
     bells
    0.81
     mosque
    0.80
     cleric
    0.79
    abad
    0.79
     occupancy
    0.79
     prayer
    0.78
     attendance
    0.77
    Activations Density 0.037%

    No Known Activations