© 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. 22637
    Prev
    Next
    INDEX
    Explanations

    instances of the word "also" indicating the inclusion of additional information or points

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    266
    +0.12
    0.7%
    465
    +0.11
    0.6%
    348
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.12
    0.03
    250
    +0.11
    0.05
    130
    +0.11
    0.07
    Negative Logits
    ¾
    -2.41
    İ
    -2.36
    ķ
    -2.31
    ĥ
    -2.30
    ij
    -2.14
    Ĭ
    -2.11
    ¨
    -2.10
    Ļ
    -2.08
    Īĺ
    -2.03
    ĭ
    -2.02
    POSITIVE LOGITS
    biamo
    1.55
     safely
    1.47
    leine
    1.45
    forge
    1.44
     Janeiro
    1.42
    babel
    1.40
    .","
    1.39
    eba
    1.38
    .',
    1.37
    evo
    1.37
    Activations Density 0.562%

    No Known Activations