© 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. 1-RES-JB
    11. 20251
    Prev
    Next
    INDEX
    Explanations

    references to the Pope

    oai_token-act-pair · gpt-3.5-turbo

    references to the pope

    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
    iable
    -0.76
    elong
    -0.75
    productive
    -0.72
    nerg
    -0.70
     Miner
    -0.68
     Cooperative
    -0.68
    iance
    -0.67
     Mines
    -0.67
    eeds
    -0.66
     srf
    -0.66
    POSITIVE LOGITS
     pope
    1.33
     pont
    1.04
    iscopal
    0.85
     ashore
    0.76
     bishop
    0.75
    icular
    0.74
     franc
    0.72
    ocalypse
    0.72
    Pope
    0.71
    romeda
    0.70
    Activations Density 0.011%

    No Known Activations