© 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. 25168
    Prev
    Next
    INDEX
    Explanations

    questions or phrases indicating methods or processes

    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
    459
    +0.10
    0.6%
    179
    +0.10
    0.5%
    85
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.10
    0.08
    179
    +0.10
    0.08
    496
    +0.10
    0.08
    Negative Logits
    achus
    -1.55
    ading
    -1.50
     wherever
    -1.45
    highlight
    -1.42
    .\"
    -1.40
    ]{}(
    -1.39
    inction
    -1.37
     whistle
    -1.36
    ellular
    -1.35
    ]{}
    -1.35
    POSITIVE LOGITS
    ĥ½
    2.39
    ↵
    1.97
    ↵↵
    1.97
    ↵
    1.97
    1.97
    ↵
    1.97
    ↵↵
    1.97
    1.97
    <|outofrange|>
    1.97
    1.97
    Activations Density 0.366%

    No Known Activations