© 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. 24285
    Prev
    Next
    INDEX
    Explanations

    structural elements or symbols typically associated with programming or markup languages

    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
    354
    +0.15
    0.9%
    203
    +0.13
    0.7%
    478
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.15
    0.05
    318
    +0.13
    0.05
    51
    +0.13
    0.04
    Negative Logits
    ļ
    -2.47
    «
    -2.25
    ¿
    -2.21
      ↵
    -2.13
    -2.13
    -2.13
    -2.13
    -2.13
    -2.13
    ↵  Âł
    -2.13
    POSITIVE LOGITS
    unreadable
    1.67
    ––––––––
    1.45
    unnumbered
    1.44
    \*](#
    1.42
    alta
    1.40
    poons
    1.40
    Panel
    1.37
    NON
    1.37
    POSE
    1.36
    Einstein
    1.32
    Activations Density 0.145%

    No Known Activations