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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 3146
    Prev
    Next
    INDEX
    Explanations

    mentions of historical events, figures, and regions, particularly related to the Ottoman Empire

    oai_token-act-pair · gpt-3.5-turbo

    references to historical leaders, empires, and regions, particularly related to the Ottoman Empire and its influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PsyNetMessage
    -0.76
    equ
    -0.74
    pos
    -0.69
    ffen
    -0.69
    FOX
    -0.68
    ingly
    -0.67
    found
    -0.66
    verted
    -0.66
    ffer
    -0.64
    roads
    -0.64
    POSITIVE LOGITS
     Sultan
    1.06
     Ottoman
    0.97
     Emir
    0.88
     Turks
    0.88
    oÄŁ
    0.85
     Empire
    0.83
     Sheikh
    0.83
     Imam
    0.82
     Recep
    0.79
     Saud
    0.76
    Activations Density 0.011%

    No Known Activations