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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 6-RES-JB
    6. 13053
    Prev
    Next
    INDEX
    Explanations

    the name "Walter" occurring within various contexts, likely focusing on different individuals named Walter and their associations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Walter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.98
    arian
    -0.91
    ateur
    -0.86
    ional
    -0.83
    unity
    -0.82
    arians
    -0.81
    ancers
    -0.80
    oral
    -0.79
    unal
    -0.77
    onal
    -0.77
    POSITIVE LOGITS
     Mond
    0.99
     Payton
    0.84
     Reed
    0.84
     Winc
    0.81
     Walter
    0.80
     Isaac
    0.77
     Sob
    0.76
     Cron
    0.74
     Benjamin
    0.73
    \\\\\\\\
    0.72
    Activations Density 0.012%

    No Known Activations