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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19617
    Prev
    Next
    INDEX
    Explanations

    references to historical or political figures, particularly focusing on Winston Churchill

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Winston" and related figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mileage
    -0.81
    onies
    -0.75
    ivid
    -0.73
    ocre
    -0.72
    cular
    -0.71
    amate
    -0.67
     lapse
    -0.66
    tone
    -0.66
    Reviewer
    -0.66
     subsistence
    -0.66
    POSITIVE LOGITS
     Churchill
    1.13
     Winston
    1.12
    ji
    0.83
     Peters
    0.81
    ufact
    0.81
    ullivan
    0.77
     Fore
    0.74
     Salem
    0.69
     Oaks
    0.68
    stown
    0.68
    Activations Density 0.009%

    No Known Activations