© 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. 25237
    Prev
    Next
    INDEX
    Explanations

    references to the Apache software organization

    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
    188
    +0.12
    0.7%
    421
    +0.12
    0.7%
    275
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    185
    +0.12
    0.03
    275
    +0.12
    0.04
    188
    +0.12
    0.03
    Negative Logits
    usk
    -1.50
     conduct
    -1.48
     grounds
    -1.46
    uning
    -1.45
    orms
    -1.44
     scheduled
    -1.43
    UNC
    -1.41
     fit
    -1.37
    UES
    -1.36
     Pursuant
    -1.35
    POSITIVE LOGITS
    ģ
    1.76
    riber
    1.61
    strom
    1.59
     arsenal
    1.55
    ÅĽci
    1.52
    ppo
    1.51
    ÃŃvel
    1.46
    etts
    1.44
    chester
    1.44
    »¿
    1.43
    Activations Density 0.099%

    No Known Activations