© 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. 1-RES-SM
    11. 27620
    Prev
    Next
    INDEX
    Explanations

    references to "stat" or "statistical" terms and concepts

    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
    503
    +0.17
    1.0%
    350
    +0.16
    1.0%
    110
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.17
    0.03
    350
    +0.16
    0.03
    110
    +0.15
    0.02
    Negative Logits
    ľĵ
    -1.66
    ĸ´
    -1.65
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.65
    ·¸
    -1.61
      ↵
    -1.60
    -1.60
    ↵
    -1.60
    -1.60
    -1.60
    ↵
    -1.60
    POSITIVE LOGITS
    ements
    2.40
    istics
    2.30
    eless
    2.15
    istical
    2.06
    utory
    1.99
    EMENT
    1.92
    ista
    1.82
    uary
    1.81
    etable
    1.79
    Counter
    1.75
    Activations Density 0.138%

    No Known Activations