© 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. 25305
    Prev
    Next
    INDEX
    Explanations

    configurations related to setup or initialization in programming contexts

    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%
    250
    +0.15
    0.9%
    392
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.16
    0.03
    250
    +0.15
    0.03
    392
    +0.14
    0.03
    Negative Logits
    rely
    -1.72
     slightest
    -1.60
    ktiv
    -1.56
    LLOW
    -1.51
     same
    -1.49
     #{
    -1.46
     "."
    -1.41
    iginally
    -1.38
     your
    -1.36
    join
    -1.35
    POSITIVE LOGITS
    igan
    2.04
    ulence
    1.98
    urations
    1.94
    urate
    1.85
    ulent
    1.83
    agna
    1.71
    stab
    1.67
    urable
    1.65
    igue
    1.64
    iga
    1.63
    Activations Density 0.016%

    No Known Activations