© 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. 0-MLP-SM
    11. 30876
    Prev
    Next
    INDEX
    Explanations

    mentions of trading

    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
    460
    +0.12
    0.6%
    408
    +0.10
    0.5%
    376
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.12
    0.02
    320
    +0.10
    0.01
    346
    +0.09
    0.02
    Negative Logits
    ij
    -2.49
    Ļª
    -2.46
    ¿
    -2.44
    µ
    -2.41
    ı
    -2.38
    Ŀ
    -2.34
    »
    -2.32
    ³
    -2.31
    ĥ½
    -2.29
    IJ
    -2.26
    POSITIVE LOGITS
     situation
    1.73
     poses
    1.69
     areas
    1.60
     scenes
    1.58
     problems
    1.55
    apore
    1.54
     circuits
    1.53
     situations
    1.53
    circuit
    1.52
     area
    1.52
    Activations Density 0.099%

    No Known Activations