© 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. 22597
    Prev
    Next
    INDEX
    Explanations

    specific product features and their functionalities

    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
    23
    +0.18
    1.0%
    92
    +0.14
    0.8%
    469
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.18
    0.05
    460
    +0.14
    0.03
    469
    +0.14
    0.05
    Negative Logits
    iska
    -1.63
    uates
    -1.63
    igt
    -1.59
    pun
    -1.56
    icles
    -1.54
    izes
    -1.54
    aturing
    -1.54
    yma
    -1.51
    icul
    -1.48
    rett
    -1.44
    POSITIVE LOGITS
    ↵
    1.93
    1.93
    1.93
    ↵
    1.93
             ↵
    1.93
    ↵
    1.93
    ↵↵
    1.93
    1.93
    1.93
    ↵  ↵
    1.93
    Activations Density 2.168%

    No Known Activations