© 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. 4-RES-JB
    11. 7299
    Prev
    Next
    INDEX
    Explanations

    mentions of historical figures, specifically Winston Churchill

    oai_token-act-pair · gpt-3.5-turbo

    prominent historical figures and their associated contexts

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

    No Comments

    Negative Logits
    irements
    -0.81
    Ķ
    -0.77
    xia
    -0.73
    ¦
    -0.69
    LOAD
    -0.66
    eanor
    -0.65
    leted
    -0.65
    markets
    -0.61
     expiration
    -0.58
    CLE
    -0.58
    POSITIVE LOGITS
    enegger
    0.92
    ufact
    0.86
    olkien
    0.80
     Lovecraft
    0.78
    agher
    0.77
    enstein
    0.76
     Kissinger
    0.76
     Spielberg
    0.73
    esque
    0.73
     Jr
    0.73
    Activations Density 0.021%

    No Known Activations