© 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. 22485
    Prev
    Next
    INDEX
    Explanations

    references to emotional or sensitive situations

    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
    63
    +0.11
    0.6%
    23
    +0.11
    0.6%
    174
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    431
    +0.11
    0.07
    119
    +0.11
    0.06
    63
    +0.10
    0.07
    Negative Logits
    ħ
    -1.86
     comprising
    -1.61
     opposed
    -1.51
    ordin
    -1.46
     spoke
    -1.42
     commission
    -1.40
     erected
    -1.35
     arranged
    -1.35
     abolished
    -1.33
     constituted
    -1.33
    POSITIVE LOGITS
    sters
    1.67
    ster
    1.67
     "$
    1.62
     \$
    1.61
    berries
    1.53
    ==========
    1.52
    "}](
    1.48
    >";
    1.41
    =====================
    1.37
    ICAN
    1.37
    Activations Density 1.988%

    No Known Activations