© 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. 2-MLP-SM
    11. 22680
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and elements

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    111
    +0.35
    2.1%
    156
    +0.27
    1.6%
    339
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.35
    0.01
    489
    +0.27
    0.01
    426
    +0.12
    0.01
    Negative Logits
    ¿½
    -2.35
    °
    -1.97
    Į
    -1.93
    Ĺ
    -1.84
    ¬
    -1.83
    ĻĤ
    -1.82
    ľ
    -1.81
    ²
    -1.78
    Ķ
    -1.77
    ¿
    -1.77
    POSITIVE LOGITS
     ourselves
    1.70
     fields
    1.55
     sight
    1.52
     herself
    1.51
     polls
    1.51
     theory
    1.48
     epidem
    1.46
    heries
    1.46
    casts
    1.42
    matics
    1.42
    Activations Density 0.020%

    No Known Activations