© 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. 26505
    Prev
    Next
    INDEX
    Explanations

    phrases indicating completion or accomplishment

    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
    441
    +0.12
    0.6%
    500
    +0.12
    0.6%
    71
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.12
    0.04
    270
    +0.12
    0.04
    201
    +0.12
    0.04
    Negative Logits
     hereto
    -1.90
     herein
    -1.84
    addle
    -1.66
    paces
    -1.56
    iers
    -1.51
     thereto
    -1.50
    ado
    -1.49
    Ł
    -1.49
    IGNED
    -1.48
    ¢
    -1.48
    POSITIVE LOGITS
     replies
    1.55
     passer
    1.43
    zing
    1.41
     riot
    1.35
     response
    1.29
    oche
    1.25
     galleries
    1.25
     zo
    1.24
    oses
    1.24
     comment
    1.24
    Activations Density 0.016%

    No Known Activations