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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 14193
    Prev
    Next
    INDEX
    Explanations

    terms related to international politics and military operations involving the U.S

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "U.S." or references to the United States

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Noir
    -0.68
     Wicked
    -0.66
     bars
    -0.65
     %%
    -0.63
     artisan
    -0.60
     Extras
    -0.56
     inacc
    -0.56
     modesty
    -0.55
     Gleaming
    -0.55
     anonym
    -0.55
    POSITIVE LOGITS
    PDATED
    1.03
    lyss
    0.96
    nexpected
    0.95
    seless
    0.93
    gly
    0.93
    zbek
    0.91
    llah
    0.90
    NA
    0.89
    psc
    0.88
    topia
    0.86
    Activations Density 0.050%

    No Known Activations