© 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. 27618
    Prev
    Next
    INDEX
    Explanations

    phrases related to coding and scripting tasks

    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
    +0.22
    1.3%
    416
    +0.17
    1.0%
    198
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    416
    +0.22
    0.03
    282
    +0.17
    0.03
    119
    +0.13
    0.01
    Negative Logits
    âĢIJ
    -1.66
    ifice
    -1.48
    Äģr
    -1.46
    ytes
    -1.43
    arman
    -1.40
    ¬
    -1.39
      ↵
    -1.37
    ishers
    -1.36
    «
    -1.36
    nis
    -1.33
    POSITIVE LOGITS
    :</
    1.67
    erville
    1.50
    :"
    1.48
     Assistant
    1.40
    ]:
    1.38
     (@
    1.37
    ,''
    1.37
    adow
    1.33
    :*
    1.32
    :&
    1.32
    Activations Density 0.214%

    No Known Activations