© 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. 2-RES-SM
    11. 10413
    Prev
    Next
    INDEX
    Explanations

    content related to programming and script execution

    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
    478
    +0.13
    0.8%
    238
    +0.12
    0.7%
    266
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    416
    +0.13
    0.01
    206
    +0.12
    0.01
    53
    +0.12
    0.01
    Negative Logits
    icum
    -1.65
    ically
    -1.62
    ĨĴ
    -1.52
     Trophy
    -1.37
     magazine
    -1.37
     dealer
    -1.36
    istical
    -1.36
    iÄĩ
    -1.36
    icro
    -1.36
    zent
    -1.35
    POSITIVE LOGITS
    ```
    1.83
    msgstr
    1.76
    uppose
    1.53
    "?"
    1.52
    "?
    1.47
    "."
    1.44
     wanna
    1.43
    ––––––––
    1.42
    over
    1.40
    rangle
    1.39
    Activations Density 0.038%

    No Known Activations