© 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. 22599
    Prev
    Next
    INDEX
    Explanations

    references to interviews and discussions related to various topics

    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
    116
    +0.16
    0.9%
    347
    +0.13
    0.8%
    437
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.16
    0.09
    116
    +0.13
    0.07
    122
    +0.12
    0.05
    Negative Logits
     hell
    -1.49
    ++)
    -1.49
    ĻĤ
    -1.46
    ĨĴ
    -1.42
    smallcaps
    -1.40
    ###
    -1.39
     pity
    -1.38
    $$
    -1.36
     sorry
    -1.32
     laughing
    -1.32
    POSITIVE LOGITS
    innings
    1.66
     Category
    1.58
    fficients
    1.53
     unanim
    1.52
     clause
    1.48
    onical
    1.48
     field
    1.42
     formula
    1.41
    hood
    1.39
     Iss
    1.38
    Activations Density 2.214%

    No Known Activations