Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 24410
    Prev
    Next
    INDEX
    Explanations

    specific name references related to a character named Rapunzel

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character "Rapunzel."

    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
     Lauder
    -0.73
     Yankee
    -0.68
     Aires
    -0.68
     Samar
    -0.67
    ertodd
    -0.65
    ++++++++++++++++
    -0.65
    selage
    -0.64
    vette
    -0.64
    perse
    -0.64
     Lebanese
    -0.63
    POSITIVE LOGITS
    acious
    1.12
    itone
    0.96
    acity
    0.93
    aic
    0.90
    hett
    0.87
    ulation
    0.86
    unct
    0.83
    quet
    0.83
    olitan
    0.83
    ograph
    0.83
    Activations Density 0.019%

    No Known Activations