© 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. 22603
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so" used in various contexts

    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
    500
    +0.15
    0.8%
    412
    +0.12
    0.7%
    274
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.15
    0.06
    100
    +0.12
    0.05
    500
    +0.12
    0.04
    Negative Logits
    ¿½
    -1.98
    theless
    -1.62
     Heat
    -1.56
    UAL
    -1.39
     ankle
    -1.36
    ¿
    -1.35
    heart
    -1.32
     brow
    -1.31
     eye
    -1.27
     CONDITIONS
    -1.27
    POSITIVE LOGITS
    plots
    1.51
    ()).
    1.50
    acter
    1.46
    pgen
    1.42
    ὶ
    1.41
    played
    1.41
    ificate
    1.39
    icles
    1.38
    allocate
    1.36
    arm
    1.36
    Activations Density 0.264%

    No Known Activations