© 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. 12941
    Prev
    Next
    INDEX
    Explanations

    variable declarations and initializations in programming 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
    285
    +0.17
    1.0%
    369
    +0.15
    0.8%
    411
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.17
    0.01
    285
    +0.15
    0.05
    379
    +0.13
    0.05
    Negative Logits
    °
    -1.75
    Ĭ
    -1.59
    ģ
    -1.55
    ¯
    -1.55
    /#
    -1.51
    coat
    -1.50
    ¿½
    -1.48
       ↵
    -1.46
    ↵Č
    -1.46
    -1.46
    POSITIVE LOGITS
    iju
    1.58
    ceedings
    1.53
    Idx
    1.52
    NdEx
    1.37
     numbered
    1.37
     Nations
    1.36
    iei
    1.35
    istani
    1.35
    ies
    1.34
    ymp
    1.33
    Activations Density 0.581%

    No Known Activations