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. 11-RES-JB
    6. 8216
    Prev
    Next
    INDEX
    Explanations

    news organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to news organizations and media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¯
    -0.73
    ership
    -0.62
     privile
    -0.61
    album
    -0.60
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.58
     screws
    -0.58
    venants
    -0.58
     chant
    -0.58
    pmwiki
    -0.57
     sled
    -0.56
    POSITIVE LOGITS
    News
    1.10
     News
    1.01
    411
    0.95
     Politics
    0.83
    news
    0.80
    Techn
    0.79
    NEWS
    0.77
     Trend
    0.75
    Politics
    0.75
    Money
    0.74
    Activations Density 0.085%

    No Known Activations