© 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. 22590
    Prev
    Next
    INDEX
    Explanations

    mentions of executive roles and titles within organizations

    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
    23
    +0.13
    0.7%
    74
    +0.12
    0.7%
    175
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.13
    0.04
    74
    +0.12
    0.02
    491
    +0.12
    0.03
    Negative Logits
    "])
    -1.70
     lately
    -1.56
    onne
    -1.44
    '])
    -1.42
    ']))
    -1.39
    (@"
    -1.38
    icago
    -1.37
     recently
    -1.37
     fm
    -1.33
    posium
    -1.29
    POSITIVE LOGITS
     mind
    1.52
    grad
    1.44
    >;
    1.42
     Cher
    1.40
     graded
    1.34
    odil
    1.31
    lop
    1.30
     Belt
    1.29
    go
    1.29
    ori
    1.28
    Activations Density 0.625%

    No Known Activations