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. 0-RES-JB
    6. 24419
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Roy" at a high activation value

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals named Roy

    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
    glers
    -0.76
    CN
    -0.73
    Ä
    -0.73
    dot
    -0.72
    è¦ļéĨĴ
    -0.71
     cat
    -0.69
     bracelet
    -0.69
    SCP
    -0.68
     wart
    -0.68
     particle
    -0.65
    POSITIVE LOGITS
     Roy
    3.83
    Roy
    3.19
     Robbie
    1.38
     Moore
    1.27
     Robin
    1.15
     Marvin
    1.14
    Moore
    1.11
     Doug
    1.07
     Clarence
    1.06
     Darrell
    1.03
    Activations Density 0.025%

    No Known Activations