© 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. 1-RES-JB
    11. 14317
    Prev
    Next
    INDEX
    Explanations

    names, particularly the name "Pulitzer" with varying degrees of activation

    oai_token-act-pair · gpt-3.5-turbo

    the name "Pitzer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.75
    con
    -0.66
    edit
    -0.65
    skirts
    -0.65
    haps
    -0.63
    angered
    -0.63
    versions
    -0.61
    spring
    -0.61
     segreg
    -0.61
    termination
    -0.59
    POSITIVE LOGITS
    itzer
    1.36
    enegger
    0.90
    zman
    0.85
    mann
    0.82
    sonian
    0.80
    rod
    0.79
    gerald
    0.77
     Bros
    0.76
    baum
    0.76
     MacArthur
    0.75
    Activations Density 0.004%

    No Known Activations