© 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. 29729
    Prev
    Next
    INDEX
    Explanations

    expressions of happiness or positivity, particularly smiles

    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
    148
    +0.14
    0.8%
    115
    +0.14
    0.8%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.14
    0.02
    382
    +0.14
    0.02
    347
    +0.13
    0.02
    Negative Logits
     ↵
    -2.80
    ↵  Âł
    -2.80
     ↵
    -2.80
     ↵
    -2.80
    č↵
    -2.80
    ↵
    -2.80
    č↵
    -2.80
    ↵↵
    -2.80
    -2.80
    -2.80
    POSITIVE LOGITS
    rpc
    2.06
    backed
    1.83
     hello
    1.71
    chitz
    1.61
    ctx
    1.58
    zc
    1.58
    caster
    1.56
    wise
    1.53
    lite
    1.50
    handler
    1.49
    Activations Density 0.024%

    No Known Activations