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. 5-RES-JB
    6. 2171
    Prev
    Next
    INDEX
    Explanations

    references to sculpting and sculptures

    oai_token-act-pair · gpt-3.5-turbo

    references to sculpture and sculpting activities

    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
     WTO
    -0.79
     Mub
    -0.72
     Witnesses
    -0.72
     rainy
    -0.66
     Heavenly
    -0.65
    CE
    -0.62
    nerg
    -0.62
     coli
    -0.61
    TPS
    -0.61
     McGr
    -0.61
    POSITIVE LOGITS
    urally
    1.26
    ured
    1.15
     sculpt
    1.08
    ulpt
    1.07
    ural
    1.03
    rator
    1.03
     sculptures
    1.01
    Artist
    0.98
    icons
    0.95
    itect
    0.92
    Activations Density 0.021%

    No Known Activations