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. 17381
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name "Pak"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Pak" and related names or entities

    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
     wildfire
    -0.84
    ŃĶ
    -0.76
     leve
    -0.70
     Lyons
    -0.68
     precedent
    -0.66
    ici
    -0.66
     Diablo
    -0.65
     Luc
    -0.64
     damned
    -0.64
     Jerome
    -0.63
    POSITIVE LOGITS
     Pak
    3.63
    Pak
    3.33
    pak
    2.76
    anka
    1.52
     Lok
    1.40
     Kang
    1.39
    pler
    1.35
     Ik
    1.28
     Buk
    1.18
     Kart
    1.18
    Activations Density 0.030%

    No Known Activations