© 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. 27147
    Prev
    Next
    INDEX
    Explanations

    instances of the word "decade" or its variations, including mentions of the month of December

    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
    444
    +0.18
    1.0%
    35
    +0.14
    0.8%
    177
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.18
    0.02
    177
    +0.14
    0.03
    350
    +0.11
    0.02
    Negative Logits
    ktiv
    -1.83
     else
    -1.58
    kan
    -1.58
    -1.52
    -1.52
    ↵↵
    -1.52
     ↵
    -1.52
    ↵
    -1.52
    ↵
    -1.52
     ↵
    -1.52
    POSITIVE LOGITS
    ipher
    2.04
    ibel
    1.79
    iseconds
    1.75
    ryption
    1.72
    eleration
    1.71
    rypted
    1.71
    umbent
    1.68
    imals
    1.66
     whistle
    1.57
    velope
    1.52
    Activations Density 0.091%

    No Known Activations