© 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. 12950
    Prev
    Next
    INDEX
    Explanations

    instances of the word "penny"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific name or character associated with the word "Penny"

    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
     nom
    -0.74
     scrolls
    -0.72
     Ba
    -0.71
     lands
    -0.66
     warm
    -0.63
     pur
    -0.63
     occult
    -0.63
     Kal
    -0.62
     resil
    -0.62
     protection
    -0.62
    POSITIVE LOGITS
    enny
    4.10
    enna
    1.40
     Penny
    1.37
    enn
    1.35
     Benny
    1.25
     Kenny
    1.13
     Jenny
    1.12
    ippi
    1.09
    illian
    1.07
    izzy
    1.07
    Activations Density 0.012%

    No Known Activations