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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11777
    Prev
    Next
    INDEX
    Explanations

    references to various types of particles and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.19
    1.1%
    502
    +0.12
    0.7%
    442
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.19
    0.02
    502
    +0.12
    0.01
    164
    +0.11
    0.02
    Negative Logits
    ĥ½
    -2.84
    ½
    -2.78
    ·
    -2.73
    Ń
    -2.61
    ·¸
    -2.59
    ¼
    -2.55
    ³
    -2.50
    §
    -2.50
    º
    -2.37
    ±
    -2.37
    POSITIVE LOGITS
    nikov
    2.09
    ellar
    2.00
    nets
    1.90
    manship
    1.88
     particles
    1.78
    oidal
    1.70
    nel
    1.69
    icles
    1.68
    ious
    1.65
     droplets
    1.57
    Activations Density 0.114%

    No Known Activations