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. 3-RES-JB
    6. 10868
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named Weiss in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the character 'Weiss' consistently throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cffffcc
    -0.77
    aneously
    -0.75
     IMAGES
    -0.72
    bably
    -0.72
    aneous
    -0.70
    anism
    -0.69
    Physical
    -0.64
     Manila
    -0.63
    vantage
    -0.63
    Indiana
    -0.63
    POSITIVE LOGITS
     Weiss
    1.08
     Schwarz
    1.06
    mann
    1.03
    Weiss
    1.01
    bach
    0.92
    enstein
    0.91
    schild
    0.86
    gang
    0.84
    ullivan
    0.80
    meyer
    0.79
    Activations Density 0.013%

    No Known Activations