© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10252
    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    194
    +0.11
    0.6%
    185
    +0.11
    0.6%
    258
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.11
    0.00
    1
    -0.11
    0.00
    2
    -0.11
    0.00
    Negative Logits
    ¹
    -3.51
    Ļª
    -3.48
    Ł
    -3.40
    Īĺ
    -3.32
    Ļ
    -3.29
    »¿
    -3.29
    ¸
    -3.27
    -3.25
    ↵↵↵
    -3.25
    -3.25
    POSITIVE LOGITS
    coli
    1.52
     vict
    1.45
     insulator
    1.43
    aeda
    1.43
    hern
    1.42
    riton
    1.36
    andals
    1.33
    Tc
    1.32
     recruits
    1.28
    acrylamide
    1.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.