© 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. 7035
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Peter" followed by a numeral

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Peter."

    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
    req
    -0.87
    eatures
    -0.78
    ornia
    -0.78
    iencies
    -0.75
    ership
    -0.70
    inately
    -0.67
    BIP
    -0.67
    ees
    -0.67
    dq
    -0.66
    erred
    -0.62
    POSITIVE LOGITS
    bilt
    1.43
    borough
    1.12
     Thiel
    0.97
    loo
    0.93
     Pan
    0.89
     Parker
    0.88
     Gabriel
    0.81
     Tosh
    0.80
     Fram
    0.80
     Panzer
    0.80
    Activations Density 0.021%

    No Known Activations