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. 1-RES-SM
    6. 26756
    Prev
    Next
    INDEX
    Explanations

    references to local communities or regions

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.22
    1.2%
    119
    +0.14
    0.8%
    30
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.22
    0.04
    476
    +0.14
    0.04
    119
    +0.12
    0.03
    Negative Logits
    ful
    -1.75
    º
    -1.70
    Ĥ¬
    -1.70
     unequal
    -1.68
     deprived
    -1.63
    Į
    -1.63
     fundamentally
    -1.62
    rin
    -1.58
    İ
    -1.50
    ĥ½
    -1.48
    POSITIVE LOGITS
    ubot
    2.30
    ised
    2.23
    ising
    2.04
    izer
    1.91
    ización
    1.88
     maxima
    1.79
    izing
    1.76
    izers
    1.68
    isation
    1.67
    ize
    1.63
    Activations Density 0.068%

    No Known Activations