© 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. 14173
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation intertwined with themes of romantic longing

    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
    478
    +0.14
    0.8%
    187
    +0.13
    0.8%
    38
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.14
    0.08
    484
    +0.13
    0.07
    187
    +0.13
    0.07
    Negative Logits
    ĥ½
    -2.39
    "}](#
    -1.77
    ģ
    -1.66
    Ł
    -1.64
    rapeut
    -1.64
    ipel
    -1.53
     syndrome
    -1.47
    £
    -1.44
    Ĵ
    -1.42
    Ĥ
    -1.42
    POSITIVE LOGITS
    noreply
    1.65
    cludes
    1.60
    egan
    1.50
    ></
    1.46
    Relative
    1.44
    imon
    1.38
    Window
    1.37
    iking
    1.34
      ↵
    1.34
    cluding
    1.33
    Activations Density 1.722%

    No Known Activations