© 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. 30874
    Prev
    Next
    INDEX
    Explanations

    structural formatting in code

    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
    311
    +0.13
    0.7%
    7
    +0.12
    0.6%
    403
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.13
    0.12
    35
    +0.12
    0.10
    322
    +0.11
    0.10
    Negative Logits
     society
    -1.72
     relationships
    -1.60
     discovery
    -1.59
    liness
    -1.56
     Relations
    -1.47
    OPLE
    -1.45
    -1.45
     Universe
    -1.45
     life
    -1.44
    stalk
    -1.44
    POSITIVE LOGITS
    ĻĤ
    2.15
    į
    2.11
    ī
    2.11
    Ĩ
    2.05
    Īĺ
    2.04
    ¶
    1.99
    Ĥ¬
    1.94
    ĨĴ
    1.86
    zzles
    1.80
    Ń
    1.77
    Activations Density 0.173%

    No Known Activations