© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 22607
    Prev
    Next
    INDEX
    Explanations

    percentage values represented in a variety of formats

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-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_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.29
    1.7%
    23
    +0.17
    1.0%
    460
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.29
    0.03
    180
    +0.17
    0.03
    170
    +0.13
    0.02
    Negative Logits
    endas
    -1.61
     combinator
    -1.50
     qué
    -1.49
     awa
    -1.49
    bery
    -1.43
    phabet
    -1.43
    cloth
    -1.43
    enda
    -1.43
    ful
    -1.41
    ()"
    -1.41
    POSITIVE LOGITS
    ®
    3.59
    §
    3.45
    Ĺ
    3.44
    ·
    3.28
    «
    3.27
    ¨
    3.22
    ¿
    3.17
    °
    3.16
    ķ
    3.14
    ij
    3.12
    Activations Density 0.215%

    No Known Activations