© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 22413
    Prev
    Next
    INDEX
    Explanations

    proper nouns that start with "Pa"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Pa" appearing with high frequency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eering
    -0.92
    schild
    -0.85
    suit
    -0.81
    dress
    -0.79
    birds
    -0.74
     Consortium
    -0.70
     Mavericks
    -0.70
    ships
    -0.69
    casting
    -0.69
    geist
    -0.69
    POSITIVE LOGITS
    izo
    1.18
    aternal
    1.01
    ige
    1.01
    ñ
    1.00
    olo
    0.99
    uter
    0.98
    xton
    0.98
    olini
    0.97
    apon
    0.93
    ignt
    0.91
    Activations Density 0.034%

    No Known Activations