© 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. 30910
    Prev
    Next
    INDEX
    Explanations

    terms related to investigations and inquiries

    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
    +0.25
    1.5%
    461
    +0.14
    0.8%
    45
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.25
    0.01
    45
    +0.14
    0.01
    356
    +0.12
    0.01
    Negative Logits
    Ĵ
    -3.93
    §
    -3.74
    <|outofrange|>
    -3.72
    ↵↵
    -3.72
    ↵
    -3.72
    č↵
    -3.72
    <|outofrange|>
    -3.72
    ↵
    -3.72
    <|outofrange|>
    -3.72
     ↵
    -3.72
    POSITIVE LOGITS
    hell
    1.98
    uppose
    1.96
    icle
    1.88
    istant
    1.84
    ystems
    1.78
    ymbol
    1.77
    ource
    1.72
    creen
    1.66
    helf
    1.64
    ilate
    1.58
    Activations Density 0.093%

    No Known Activations