© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 30287
    Prev
    Next
    INDEX
    Explanations

    instances of the word "call."

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    395
    +0.14
    0.8%
    134
    +0.11
    0.6%
    330
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.14
    0.04
    472
    +0.11
    0.04
    162
    +0.11
    0.04
    Negative Logits
    iens
    -1.64
    umbs
    -1.42
    ↵		↵
    -1.41
    ances
    -1.39
     idle
    -1.37
    .’”
    -1.33
     comprehension
    -1.32
    ANCE
    -1.32
    .''
    -1.30
    ubot
    -1.29
    POSITIVE LOGITS
    culos
    1.57
     sake
    1.57
    culo
    1.55
     chosen
    1.50
    heimer
    1.43
    quez
    1.42
    clerosis
    1.39
    ulf
    1.39
    aris
    1.36
    oriented
    1.35
    Activations Density 0.016%

    No Known Activations