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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 8-RES-JB
    6. 5413
    Prev
    Next
    INDEX
    Explanations

    multi-syllable words that contain a stress on the third-to-last syllable

    oai_token-act-pair · gpt-3.5-turbo

    references to family lineage and heritage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ATK
    -0.55
     Upper
    -0.51
     fasting
    -0.50
     shutter
    -0.48
     perpet
    -0.48
     SHARES
    -0.48
     Mt
    -0.47
     EDITION
    -0.47
     EDT
    -0.46
     RIS
    -0.46
    POSITIVE LOGITS
    merce
    0.81
    alion
    0.81
    kees
    0.78
    zee
    0.78
    lear
    0.76
    ª
    0.74
    amera
    0.73
    ī
    0.72
    idy
    0.70
    ooks
    0.70
    Activations Density 1.324%

    No Known Activations