© 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. 25133
    Prev
    Next
    INDEX
    Explanations

    terms related to approximation and estimation in various contexts

    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
    86
    +0.14
    0.8%
    376
    +0.12
    0.7%
    352
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    257
    +0.14
    0.01
    86
    +0.12
    0.01
    83
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.56
    Į
    -2.35
    ©
    -2.27
    ĻĤ
    -2.10
    ½
    -2.10
    į
    -2.05
    ľĵ
    -2.01
    IJ
    -1.90
    ¯
    -1.89
    §
    -1.88
    POSITIVE LOGITS
    ulous
    1.85
     safe
    1.71
    worth
    1.61
     difficulty
    1.54
     errors
    1.54
    cias
    1.51
    able
    1.51
    iary
    1.50
     safety
    1.49
    igraphy
    1.48
    Activations Density 0.007%

    No Known Activations