© 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. 4-RES-SM
    11. 11405
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    217
    +0.15
    0.9%
    273
    +0.12
    0.7%
    331
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.15
    0.00
    1
    -0.12
    0.00
    2
    -0.11
    0.00
    Negative Logits
    ¾
    -6.06
    ↵
    -6.05
    ↵↵
    -6.05
    -6.05
    -6.05
    -6.05
     ↵
    -6.05
    ↵
    -6.05
    ↵
    -6.05
    ↵  ↵
    -6.05
    POSITIVE LOGITS
    opoulos
    1.66
     fair
    1.48
    ipe
    1.43
    ffect
    1.42
    ès
    1.37
     similar
    1.35
    ä
    1.32
     comparable
    1.30
     reserv
    1.29
     Val
    1.29
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.