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. 1-RES-JB
    6. 18504
    Prev
    Next
    INDEX
    Explanations

    distinctive words related to particle physics, specifically 'quarks' and 'antiquarks'

    oai_token-act-pair · gpt-3.5-turbo

    references to quarks and their interactions in particle physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calcul
    -0.76
     frail
    -0.72
     breast
    -0.70
     dime
    -0.68
     surg
    -0.67
     fragile
    -0.65
     actu
    -0.65
     cervical
    -0.64
    atever
    -0.64
     politic
    -0.64
    POSITIVE LOGITS
    arks
    1.30
    manship
    1.01
    ertodd
    0.93
    afety
    0.83
    eele
    0.79
    anse
    0.79
    holders
    0.77
    esian
    0.77
    tyard
    0.76
    oons
    0.76
    Activations Density 0.004%

    No Known Activations