© 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. 1-RES-SM
    11. 26185
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    178
    +0.14
    0.8%
    125
    +0.14
    0.8%
    495
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    -0.14
    0.00
    1
    -0.14
    0.00
    2
    -0.12
    0.00
    Negative Logits
    .[@
    -1.46
    [@
    -1.39
    \[[@
    -1.39
     encephal
    -1.38
    ADS
    -1.37
    stone
    -1.35
    ega
    -1.34
     alanine
    -1.31
     disordered
    -1.30
    otry
    -1.30
    POSITIVE LOGITS
    ĻĤ
    2.33
    ¿½
    1.99
    Ĥ
    1.92
    ials
    1.76
    Ļª
    1.73
    ¸
    1.67
    ¦
    1.60
    ¿
    1.58
    sters
    1.58
     deposition
    1.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.