© 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. 0-RES-JB
    11. 1984
    Prev
    Next
    INDEX
    Explanations

    words related to the brand or person "Rizzo."

    oai_token-act-pair · gpt-3.5-turbo

    the occurrences of the term "Rizzo" or related variations

    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
     attached
    -0.70
     attach
    -0.70
     attaching
    -0.68
     Norn
    -0.68
     subsistence
    -0.66
     express
    -0.65
     Recon
    -0.63
     export
    -0.63
     ordinarily
    -0.63
     square
    -0.62
    POSITIVE LOGITS
    izz
    4.45
    izzle
    2.04
    izzy
    1.73
    iz
    1.53
    izzard
    1.49
    azz
    1.43
    izza
    1.42
    IZ
    1.42
    uzz
    1.35
    onz
    1.19
    Activations Density 0.016%

    No Known Activations