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. 1-RES-JB
    6. 24436
    Prev
    Next
    INDEX
    Explanations

    the last name "Frieden" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Fried" in various contextual scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obbies
    -0.75
    ctica
    -0.73
    avez
    -0.72
    auga
    -0.71
     Pradesh
    -0.65
    ifles
    -0.65
    ctic
    -0.64
    Downloadha
    -0.64
    aucas
    -0.62
    aths
    -0.62
    POSITIVE LOGITS
     Fried
    1.39
    enstein
    1.00
    erick
    0.97
     Dahl
    0.96
    linger
    0.95
    glers
    0.93
    fried
    0.93
     Krug
    0.90
    haus
    0.89
    wald
    0.88
    Activations Density 0.011%

    No Known Activations