© 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. 1-RES-SM
    11. 25688
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures, including variable declarations and method invocations

    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/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
    369
    +0.12
    0.7%
    240
    +0.12
    0.7%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.12
    0.16
    479
    +0.12
    0.10
    316
    +0.11
    0.10
    Negative Logits
    »¿
    -2.66
    ¤
    -2.65
    Ļ
    -2.64
    ĸ
    -2.56
    Ķ
    -2.49
    ģ
    -2.46
    ĨĴ
    -2.44
    -2.44
    -2.44
    -2.44
    POSITIVE LOGITS
     skating
    1.51
     fir
    1.42
     themselves
    1.40
    itivity
    1.38
     corps
    1.38
     rapidly
    1.37
    nego
    1.36
     contral
    1.36
    :_
    1.35
     coord
    1.34
    Activations Density 1.694%

    No Known Activations