© 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. 22399
    Prev
    Next
    INDEX
    Explanations

    programming function definitions and method calls

    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
    510
    +0.14
    0.8%
    175
    +0.12
    0.7%
    283
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    235
    +0.14
    0.09
    50
    +0.12
    0.03
    56
    +0.12
    0.09
    Negative Logits
    ellite
    -1.63
    emitting
    -1.56
     ${
    -1.47
    acters
    -1.44
    ctors
    -1.44
    ename
    -1.40
    disambiguation
    -1.39
    ths
    -1.39
    orted
    -1.37
    ctions
    -1.36
    POSITIVE LOGITS
    ĥ
    2.27
    ¡
    2.09
    Į
    1.92
    »¿
    1.89
    isco
    1.88
    º
    1.87
    ²
    1.86
    ¹
    1.83
    ½
    1.83
    ¬
    1.76
    Activations Density 1.365%

    No Known Activations