© 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. 0-RES-JB
    11. 19258
    Prev
    Next
    INDEX
    Explanations

    references to the name "Paul"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Paul."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izen
    -0.78
    TL
    -0.71
    sys
    -0.67
    ahime
    -0.67
     retri
    -0.65
    estation
    -0.64
    HI
    -0.62
    ifi
    -0.62
     wast
    -0.62
     HDD
    -0.62
    POSITIVE LOGITS
     Paul
    3.43
    Paul
    2.92
     Paula
    1.60
     Peter
    1.49
     Ron
    1.46
     Anthony
    1.38
     Ryan
    1.37
     Stephen
    1.35
     Philipp
    1.34
     John
    1.32
    Activations Density 0.022%

    No Known Activations