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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28096
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "widow" or related terms indicating loss

    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
    59
    +0.15
    0.9%
    244
    +0.13
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.15
    0.01
    59
    +0.13
    0.01
    325
    +0.12
    0.01
    Negative Logits
     Circuit
    -1.51
    onitrile
    -1.50
    asta
    -1.47
    yet
    -1.43
    akes
    -1.31
    tes
    -1.29
     Evening
    -1.27
    arma
    -1.27
    ureus
    -1.27
     maid
    -1.27
    POSITIVE LOGITS
    ĻĤ
    2.62
    Ĵ
    2.57
    ¢
    2.53
    ĭ
    2.53
    ª
    2.52
    ī
    2.48
    Į
    2.45
    ł
    2.44
    ¡
    2.41
    ±
    2.40
    Activations Density 3.577%

    No Known Activations