© 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. 11-RES-JB
    11. 17648
    Prev
    Next
    INDEX
    Explanations

    historical and philosophical figures' names

    oai_token-act-pair · gpt-3.5-turbo

    references to notable historical figures in evolutionary theory and philosophy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olulu
    -0.85
     Whip
    -0.69
     Rahul
    -0.69
     Benghazi
    -0.67
     GoPro
    -0.67
     PSP
    -0.67
    aspx
    -0.65
     Kodi
    -0.65
     MSI
    -0.63
     Jason
    -0.62
    POSITIVE LOGITS
    ian
    1.36
    ians
    1.11
    schild
    0.99
     himself
    0.98
    icism
    0.97
    ism
    0.96
    sonian
    0.95
    Books
    0.91
    isms
    0.89
    anism
    0.88
    Activations Density 0.154%

    No Known Activations