© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 30452
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "no."

    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
    497
    +0.14
    0.8%
    391
    +0.13
    0.7%
    317
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.14
    0.04
    391
    +0.13
    0.03
    358
    +0.12
    0.03
    Negative Logits
    ĨĴ
    -1.78
    anium
    -1.76
    lain
    -1.59
    nes
    -1.56
    anson
    -1.54
    »
    -1.54
    rophy
    -1.49
    night
    -1.49
    entary
    -1.49
    ĥ½
    -1.42
    POSITIVE LOGITS
    pe
    1.85
    zzles
    1.82
    isy
    1.79
    ises
    1.79
     longer
    1.79
    ethe
    1.75
     deal
    1.75
    velle
    1.73
    zzle
    1.68
    bles
    1.68
    Activations Density 1.268%

    No Known Activations