© 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. 22634
    Prev
    Next
    INDEX
    Explanations

    terms related to disease processes and their development

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    155
    +0.13
    0.7%
    250
    +0.13
    0.7%
    289
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.13
    0.03
    394
    +0.13
    0.03
    155
    +0.12
    0.03
    Negative Logits
    ĻĤ
    -5.54
    Ĺ
    -5.44
    IJ
    -5.37
    ı
    -5.36
    ł
    -5.34
    £
    -5.28
    ľ
    -5.24
    ĨĴ
    -5.22
    ↵
    -5.17
    -5.17
    POSITIVE LOGITS
    "|
    1.68
    ”,
    1.63
    "</
    1.59
     performers
    1.57
    ”—
    1.57
    rolet
    1.53
    .“
    1.52
    ”:
    1.50
    =”
    1.45
    anza
    1.43
    Activations Density 0.126%

    No Known Activations