© 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. 27222
    Prev
    Next
    INDEX
    Explanations

    references to direct actions or contacts

    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
    404
    +0.15
    0.8%
    156
    +0.12
    0.7%
    438
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.15
    0.02
    343
    +0.12
    0.02
    334
    +0.12
    0.02
    Negative Logits
    cules
    -1.66
    crets
    -1.61
    pace
    -1.57
    abeth
    -1.52
    psy
    -1.51
    aves
    -1.48
    pt
    -1.46
    adelphia
    -1.46
     new
    -1.46
     locker
    -1.41
    POSITIVE LOGITS
    amente
    2.22
    ivity
    2.05
    itud
    1.83
    ively
    1.77
    erad
    1.72
    ive
    1.62
     Redistributions
    1.59
    rice
    1.56
    going
    1.49
    eur
    1.46
    Activations Density 0.072%

    No Known Activations