© 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 EvalsExportsinterp-engineNEWAPI 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. 13327
    Prev
    Next
    INDEX
    Explanations

    specific programming structures and keywords related to functionalities or attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.21
    1.2%
    284
    +0.14
    0.8%
    369
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.21
    0.05
    484
    +0.14
    0.07
    17
    +0.14
    0.00
    Negative Logits
    ¢
    -4.00
    ↵↵
    -3.98
    ↵
    -3.98
    -3.98
    -3.98
    č↵
    -3.98
    ↵↵
    -3.98
    ↵↵
    -3.98
    ↵
    -3.98
    -3.98
    POSITIVE LOGITS
    Delegate
    1.39
     Serum
    1.38
    zona
    1.38
     Trustee
    1.33
     Equal
    1.31
     Assistant
    1.31
     Redist
    1.29
     Investment
    1.28
     Economic
    1.27
     Depression
    1.27
    Activations Density 2.977%

    No Known Activations