© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 8660
    Prev
    Next
    INDEX
    Explanations

    elements related to inventions, proposals, and formal declarations or rulings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    334
    +0.13
    0.7%
    216
    +0.12
    0.7%
    501
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.13
    0.00
    458
    +0.12
    0.00
    334
    +0.12
    0.01
    Negative Logits
    OOGLE
    -1.84
    lining
    -1.70
    nt
    -1.48
    tering
    -1.45
    inux
    -1.44
     Expect
    -1.44
    adeon
    -1.43
     anymore
    -1.41
    ickets
    -1.41
    acion
    -1.38
    POSITIVE LOGITS
     disclosed
    2.69
     relates
    2.50
     embodiments
    2.46
     invention
    2.40
    ²
    2.27
     discloses
    2.25
    §
    2.22
    ©
    2.15
     pertains
    2.05
    ŀ
    2.03
    Activations Density 0.010%

    No Known Activations