© 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. Residuals
    9. 2-RES-SM
    11. 12709
    Prev
    Next
    INDEX
    Explanations

    employee identification and management data

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-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_resid_post
    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
    384
    +0.11
    0.6%
    23
    +0.11
    0.6%
    494
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.11
    0.07
    232
    +0.11
    0.07
    271
    +0.10
    -0.01
    Negative Logits
    ↵
    -2.02
    )^[@
    -1.81
    ↵
    -1.70
    ↵
    -1.64
    ,^[@
    -1.60
    âĢIJ
    -1.58
    ↵
    -1.58
     ([**
    -1.58
    .^[@
    -1.57
     {#
    -1.57
    POSITIVE LOGITS
    ĻĤ
    2.63
    ·¸
    2.26
    ľĵ
    2.15
    Īĺ
    2.14
    Ķ
    2.10
    ¿
    2.02
    ¿½
    2.00
    į
    1.99
    ĭ
    1.98
    ŀ
    1.96
    Activations Density 0.600%

    No Known Activations