© 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. 30940
    Prev
    Next
    INDEX
    Explanations

    terms related to food ingredients

    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
    +0.27
    1.6%
    376
    +0.15
    0.9%
    163
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.27
    0.02
    407
    +0.15
    0.02
    329
    +0.13
    0.02
    Negative Logits
    ĥ½
    -2.58
    Ń
    -2.29
    §
    -2.21
    ĸ´
    -2.17
    °
    -2.15
    č↵
    -2.04
     ↵
    -2.04
    ↵
    -2.04
    <|outofrange|>
    -2.04
    ↵
    -2.04
    POSITIVE LOGITS
    etic
    1.55
     therein
    1.49
    asse
    1.48
    existent
    1.44
    scene
    1.44
    block
    1.43
     registers
    1.43
     triggers
    1.42
    fors
    1.42
    ential
    1.41
    Activations Density 0.020%

    No Known Activations