© 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. 25306
    Prev
    Next
    INDEX
    Explanations

    terms related to increasing stakes or raising levels of commitment

    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
    362
    +0.14
    0.8%
    293
    +0.13
    0.8%
    178
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.14
    0.01
    90
    +0.13
    0.01
    266
    +0.12
    0.01
    Negative Logits
    here
    -1.79
     entirety
    -1.62
    orect
    -1.53
     characterized
    -1.50
    IPE
    -1.49
    rely
    -1.48
    uously
    -1.48
    akia
    -1.46
    |_{
    -1.43
    TY
    -1.41
    POSITIVE LOGITS
    cedent
    2.09
    gart
    1.75
    bellum
    1.64
     clar
    1.61
    borg
    1.59
     jug
    1.57
    ÅĽci
    1.53
    vä
    1.53
     brothers
    1.52
    fessor
    1.50
    Activations Density 0.282%

    No Known Activations