© 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. 22547
    Prev
    Next
    INDEX
    Explanations

    references to technical details and code implementation in programming contexts

    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
    64
    +0.12
    0.7%
    203
    +0.12
    0.7%
    444
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.12
    0.10
    386
    +0.12
    0.06
    363
    +0.11
    0.10
    Negative Logits
    ·
    -2.37
    ²
    -2.29
    ¨
    -2.27
    ĩ
    -2.22
    ¢
    -2.18
    ¯
    -2.08
    °
    -2.07
    «
    -2.00
    ī
    -2.00
    Ĺ
    -1.99
    POSITIVE LOGITS
    /@
    1.62
    aria
    1.60
    imon
    1.49
    naire
    1.46
    elian
    1.42
     english
    1.38
    isse
    1.37
    oire
    1.36
    !!!
    1.34
    imony
    1.33
    Activations Density 1.011%

    No Known Activations