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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 13317
    Prev
    Next
    INDEX
    Explanations

    the name "Patrice" and various related terms, potentially focusing on legal, medical, and athletic contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or terms, predominantly the name "Patrice" and variations of "rand."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opol
    -0.64
    myra
    -0.64
    rypt
    -0.64
    lar
    -0.63
     thickness
    -0.62
    alach
    -0.61
    rip
    -0.60
    oub
    -0.59
     cliff
    -0.59
     gloss
    -0.59
    POSITIVE LOGITS
    ption
    1.00
    cules
    0.90
    llo
    0.88
    lli
    0.84
     Royale
    0.82
    ãĥ¼ãĥĨãĤ£
    0.82
     Paste
    0.82
    ç·
    0.81
    llor
    0.81
    ments
    0.77
    Activations Density 0.051%

    No Known Activations