© 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. 31109
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical data related to statistics

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    273
    +0.14
    0.7%
    283
    +0.13
    0.7%
    29
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    273
    +0.14
    0.08
    283
    +0.13
    0.07
    245
    +0.11
    0.06
    Negative Logits
    ±
    -1.96
    «
    -1.61
    APTER
    -1.59
    Ń
    -1.58
     ')
    -1.53
    ---|---|---
    -1.50
    '">
    -1.50
    Inflater
    -1.40
    )](#
    -1.37
     sorted
    -1.37
    POSITIVE LOGITS
     Against
    1.52
     Sans
    1.48
     defence
    1.46
    ennes
    1.43
    rooms
    1.42
     offenses
    1.37
    enty
    1.37
     defense
    1.37
    colon
    1.37
    enders
    1.34
    Activations Density 1.617%

    No Known Activations