© 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. 25307
    Prev
    Next
    INDEX
    Explanations

    instances of the word "comparative" and its variations

    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
    156
    +0.18
    1.0%
    368
    +0.13
    0.7%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.18
    0.01
    266
    +0.13
    0.01
    328
    +0.12
    0.01
    Negative Logits
    owed
    -1.69
    paces
    -1.59
    []{
    -1.58
    OW
    -1.55
    ridge
    -1.43
    ____________
    -1.43
    Category
    -1.40
    ĨĴ
    -1.38
    ows
    -1.38
    ellow
    -1.35
    POSITIVE LOGITS
    ist
    1.73
     sized
    1.59
    opan
    1.51
     gamb
    1.49
     pursu
    1.42
    zilla
    1.38
    zol
    1.36
     viewpoint
    1.35
    asy
    1.34
    vous
    1.33
    Activations Density 0.015%

    No Known Activations