© 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. 25293
    Prev
    Next
    INDEX
    Explanations

    expressions indicating inequality or comparisons

    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
    478
    +0.18
    1.0%
    376
    +0.17
    0.9%
    397
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.18
    0.03
    397
    +0.17
    0.03
    294
    +0.13
    0.02
    Negative Logits
    lement
    -1.58
    erate
    -1.50
    Category
    -1.48
    ling
    -1.46
    azine
    -1.46
    rese
    -1.44
    ing
    -1.43
    ider
    -1.41
    »¿
    -1.41
    olymer
    -1.40
    POSITIVE LOGITS
    wan
    1.52
    oha
    1.49
     fuck
    1.48
    amais
    1.45
     ple
    1.43
     ."
    1.42
     nets
    1.38
     mur
    1.37
    jam
    1.36
    ...'
    1.32
    Activations Density 0.038%

    No Known Activations