© 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. 22499
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "present" and related forms indicating existence or occurrence

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.26
    1.5%
    283
    +0.14
    0.8%
    273
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.26
    0.05
    122
    +0.14
    0.02
    283
    +0.13
    0.04
    Negative Logits
    $).
    -1.92
    $),
    -1.67
    ftware
    -1.60
     =>
    -1.59
    ITED
    -1.54
    $)
    -1.53
    ”).
    -1.52
    .",
    -1.51
    CBC
    -1.50
     appreciated
    -1.49
    POSITIVE LOGITS
     Tory
    1.44
    ativity
    1.39
    bootstrap
    1.35
     Lane
    1.30
    opause
    1.29
     Barry
    1.29
     tight
    1.28
     spot
    1.28
     Bryan
    1.27
     stages
    1.26
    Activations Density 0.581%

    No Known Activations