© 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. 2-RES-JB
    11. 5594
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to historical figures with surnames

    oai_token-act-pair · gpt-3.5-turbo

    names of influential figures, particularly artists and scholars

    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
    ebook
    -0.88
    apple
    -0.83
    eval
    -0.77
    ership
    -0.74
    llular
    -0.74
    hib
    -0.73
    agra
    -0.72
    hig
    -0.72
    river
    -0.71
    eat
    -0.70
    POSITIVE LOGITS
     Gustav
    1.24
    sson
    1.18
     Friedrich
    1.14
     Wolfgang
    1.03
     Tobias
    0.97
     Werner
    0.97
    sein
    0.95
    stadt
    0.94
     Kepler
    0.92
     Johann
    0.90
    Activations Density 0.021%

    No Known Activations