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. 10-RES-JB
    6. 15578
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant events or records being achieved

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or milestones associated with a sitting president

    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
    DragonMagazine
    -0.74
    terness
    -0.74
     beware
    -0.66
    çīĪ
    -0.64
    ernels
    -0.62
    ãĤ³
    -0.60
     Become
    -0.60
    govtrack
    -0.60
    èĪ
    -0.60
    Vers
    -0.60
    POSITIVE LOGITS
     any
    1.20
     anything
    1.03
     mankind
    1.02
     anywhere
    1.02
     humankind
    1.01
     ANY
    0.98
     anyone
    0.95
     anybody
    0.91
     EVER
    0.90
     ever
    0.85
    Activations Density 0.276%

    No Known Activations