© 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. 9-RES-JB
    11. 15751
    Prev
    Next
    INDEX
    Explanations

    references to historical figures, particularly Winston Churchill

    oai_token-act-pair · gpt-3.5-turbo

    mentions of historical or notable figures, particularly Winston Churchill

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itate
    -0.71
    itated
    -0.69
    IRO
    -0.67
    alysis
    -0.67
    ities
    -0.67
    >>>>>>>>
    -0.66
    tarians
    -0.66
    nery
    -0.66
    uce
    -0.65
    cle
    -0.64
    POSITIVE LOGITS
     Churchill
    1.32
    enburg
    0.77
    ufact
    0.75
    minster
    0.74
     Peters
    0.73
    ipeg
    0.72
    age
    0.71
    llor
    0.68
    fur
    0.68
    endor
    0.67
    Activations Density 0.119%

    No Known Activations