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. 8-RES-JB
    6. 7451
    Prev
    Next
    INDEX
    Explanations

    phrases related to energy companies and advancements in renewable energy

    oai_token-act-pair · gpt-3.5-turbo

    quantitative references related to significant sums of money

    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
    •single token firings
    Individually fires on "MRI", " Medicaid", "Dual", "Understanding", " loophole", ..."DNA", ..."RNA", ...

    No Comments

    Negative Logits
    renheit
    -0.65
     behav
    -0.57
     advoc
    -0.55
     Vaugh
    -0.55
     vulner
    -0.53
    Ire
    -0.52
     prest
    -0.52
    emale
    -0.52
    agra
    -0.51
    *.
    -0.51
    POSITIVE LOGITS
    ¶
    0.61
     Learns
    0.56
     Shin
    0.54
    zbollah
    0.53
     Roof
    0.52
     largeDownload
    0.52
     Morsi
    0.52
     Trudeau
    0.52
     Maul
    0.51
    Ĥª
    0.50
    Activations Density 1.388%

    No Known Activations