© 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. 7-RES-JB
    11. 1555
    Prev
    Next
    INDEX
    Explanations

    phrases or names related to the name "Penny."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Penny" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioch
    -0.82
    iola
    -0.80
    ifier
    -0.76
    iour
    -0.76
    IAL
    -0.73
    ifies
    -0.72
     Dragonbound
    -0.71
    icity
    -0.70
    ité
    -0.69
    icted
    -0.68
    POSITIVE LOGITS
    wise
    0.86
     Arcade
    0.84
     dreadful
    0.74
    acht
    0.71
     peg
    0.70
    cook
    0.68
    pole
    0.68
    ollar
    0.68
    roach
    0.67
    stick
    0.67
    Activations Density 0.045%

    No Known Activations