© 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. 0-MLP-SM
    11. 25213
    Prev
    Next
    INDEX
    Explanations

    references to functions or methods in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    265
    +0.12
    0.7%
    26
    +0.12
    0.6%
    358
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.12
    0.11
    35
    +0.12
    0.09
    322
    +0.11
    0.10
    Negative Logits
    »¿
    -3.44
    ¯
    -3.17
    ¨
    -3.00
    £
    -2.96
    ¡
    -2.87
    Ĺ
    -2.85
    ·¸
    -2.84
    ↵↵
    -2.84
    -2.84
    ↵
    -2.84
    POSITIVE LOGITS
     cov
    1.62
    ocene
    1.51
     globally
    1.48
    bys
    1.45
     presidents
    1.43
     worldwide
    1.41
     nom
    1.39
     EA
    1.38
     symbolic
    1.36
     Xi
    1.34
    Activations Density 0.158%

    No Known Activations