© 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. 10222
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Pete" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Pete."

    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
    ipeg
    -0.86
    Liter
    -0.73
    hips
    -0.71
     vector
    -0.70
     preval
    -0.69
    animous
    -0.68
    Iraq
    -0.67
    spring
    -0.63
    externalActionCode
    -0.63
     condem
    -0.63
    POSITIVE LOGITS
     Pete
    1.13
     Pag
    0.89
    ertodd
    0.87
     Olson
    0.84
     Roz
    0.83
     Owens
    0.77
    oshenko
    0.76
    swick
    0.75
     Carroll
    0.74
     Doodle
    0.74
    Activations Density 0.006%

    No Known Activations