© 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. 22448
    Prev
    Next
    INDEX
    Explanations

    phrases related to following or subscribing to content

    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
    16
    +0.12
    0.7%
    247
    +0.12
    0.7%
    221
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.12
    0.04
    219
    +0.12
    0.04
    70
    +0.12
    0.03
    Negative Logits
    ?).
    -1.63
    ©
    -1.55
    !),
    -1.54
     choosing
    -1.51
     lightly
    -1.45
    ?’
    -1.43
    !)
    -1.40
    !).
    -1.39
    cent
    -1.39
    ?!
    -1.37
    POSITIVE LOGITS
    ses
    1.90
    icense
    1.50
    ii
    1.50
    aughters
    1.48
    ented
    1.47
    urches
    1.47
    iei
    1.46
    ails
    1.45
    áĢ¬
    1.45
    ipes
    1.45
    Activations Density 0.516%

    No Known Activations