© 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. 27526
    Prev
    Next
    INDEX
    Explanations

    phrases related to problem-solving

    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
    317
    +0.13
    0.8%
    376
    +0.13
    0.7%
    282
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.13
    0.03
    344
    +0.13
    0.04
    317
    +0.13
    0.03
    Negative Logits
    ears
    -1.69
     flown
    -1.63
     topped
    -1.61
     recruited
    -1.59
     sailed
    -1.59
    oons
    -1.59
    Äij
    -1.54
     invaded
    -1.53
     screened
    -1.53
     voted
    -1.52
    POSITIVE LOGITS
     puzzles
    2.22
     problems
    1.88
     mysteries
    1.84
     Problems
    1.82
     Problem
    1.78
     puzzle
    1.77
    Solution
    1.75
     problem
    1.71
     equations
    1.71
    ive
    1.70
    Activations Density 0.220%

    No Known Activations