© 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. 22433
    Prev
    Next
    INDEX
    Explanations

    phrases related to visibility or recognition of people and events

    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
    487
    +0.14
    0.8%
    269
    +0.11
    0.6%
    197
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.14
    0.04
    487
    +0.11
    0.05
    67
    +0.11
    0.06
    Negative Logits
    shoot
    -1.51
     extinct
    -1.48
     rubbish
    -1.47
     urgent
    -1.45
    vast
    -1.38
     Same
    -1.36
     lt
    -1.35
     needed
    -1.33
     BASIS
    -1.31
     beaten
    -1.31
    POSITIVE LOGITS
    Ģ
    1.94
    ª
    1.92
    ī
    1.83
    Ĭ
    1.80
    ģ
    1.72
    «
    1.71
    ker
    1.70
    ł
    1.70
    Ŀ
    1.67
    ĻĤ
    1.67
    Activations Density 0.531%

    No Known Activations