© 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. 26177
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    350
    +0.13
    0.7%
    313
    +0.11
    0.6%
    354
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.13
    0.00
    1
    -0.11
    0.00
    2
    -0.11
    0.00
    Negative Logits
     preponderance
    -1.88
    Ĥ
    -1.73
    Ħ
    -1.67
    ·¸
    -1.63
    ply
    -1.60
    ±
    -1.60
    ality
    -1.58
    athing
    -1.57
    inde
    -1.55
    ership
    -1.55
    POSITIVE LOGITS
    hores
    1.67
    chen
    1.60
    anov
    1.54
    eten
    1.40
     forbidden
    1.37
    ection
    1.35
    !'
    1.35
     cursed
    1.33
    !_
    1.27
    ?_
    1.26
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.