© 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. 27386
    Prev
    Next
    INDEX
    Explanations

    references to weeks and time

    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
    477
    +0.12
    0.7%
    29
    +0.11
    0.6%
    182
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.12
    0.05
    374
    +0.11
    0.05
    288
    +0.11
    0.04
    Negative Logits
    Ĵ
    -3.53
    Ŀ
    -3.15
    ¤
    -3.07
    Ĩ
    -3.04
           ↵
    -3.01
    ↵
    -3.01
     ↵
    -3.01
    -3.01
    -3.01
    ↵↵↵
    -3.01
    POSITIVE LOGITS
    lies
    2.39
    mare
    1.91
    dream
    1.90
    iers
    1.89
    robe
    1.80
    enden
    1.79
    set
    1.75
    night
    1.73
    end
    1.72
    wide
    1.70
    Activations Density 0.294%

    No Known Activations