© 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. 25251
    Prev
    Next
    INDEX
    Explanations

    terms related to railway systems and infrastructure

    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
    +0.16
    0.9%
    362
    +0.12
    0.7%
    404
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    228
    +0.16
    0.01
    404
    +0.12
    0.01
    375
    +0.12
    0.01
    Negative Logits
     fois
    -1.49
    EVER
    -1.45
     Hurricane
    -1.39
     hope
    -1.39
     uploaded
    -1.37
     tide
    -1.33
    yla
    -1.32
     another
    -1.31
     Fly
    -1.30
     kay
    -1.29
    POSITIVE LOGITS
    ŀ
    2.01
    ®
    1.96
    ²
    1.84
    Īĺ
    1.84
    »¿
    1.84
    ĭ
    1.82
    ĸ
    1.80
    ĻĤ
    1.78
    ¢
    1.78
    Ł
    1.76
    Activations Density 0.010%

    No Known Activations