© 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. 22439
    Prev
    Next
    INDEX
    Explanations

    themes related to futurism and the interplay of technology with societal issues

    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
    76
    +0.12
    0.6%
    491
    +0.11
    0.6%
    251
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    491
    +0.12
    0.12
    249
    +0.11
    0.14
    446
    +0.11
    0.08
    Negative Logits
    blogger
    -1.69
    izoph
    -1.62
    leep
    -1.57
    cdn
    -1.56
    ftware
    -1.48
    chool
    -1.42
    ![**
    -1.41
    jsfiddle
    -1.40
    -1.39
              ↵
    -1.39
    POSITIVE LOGITS
    ity
    1.65
    ificance
    1.64
    acious
    1.57
     Ont
    1.52
    iness
    1.50
     orders
    1.43
    iating
    1.43
    ities
    1.41
    liness
    1.36
     first
    1.36
    Activations Density 2.609%

    No Known Activations