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. 2-RES-JB
    6. 1118
    Prev
    Next
    INDEX
    Explanations

    names related to a specific person, possibly a news figure named Zhang Miaomiao, Qiao Mu, or Sao

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific name or identifier

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥ³
    -0.88
    ãĥ¼ãĥĨ
    -0.83
    usable
    -0.78
    gewater
    -0.77
    iard
    -0.74
    phas
    -0.70
    ifiable
    -0.68
    CAP
    -0.68
    MER
    -0.68
     LCS
    -0.66
    POSITIVE LOGITS
    iao
    1.19
     Qiao
    0.83
     Lung
    0.83
     streng
    0.80
    oche
    0.79
     tong
    0.77
     concess
    0.75
    heng
    0.75
    gow
    0.74
    xual
    0.71
    Activations Density 0.009%

    No Known Activations