© 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. 2-RES-SM
    11. 32444
    Prev
    Next
    INDEX
    Explanations

    references to clinical contexts and studies

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.18
    1.1%
    87
    +0.12
    0.7%
    123
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.18
    0.00
    343
    +0.12
    0.01
    443
    +0.12
    0.01
    Negative Logits
    gnu
    -1.48
     certain
    -1.41
    went
    -1.36
    xit
    -1.34
    aked
    -1.33
    urope
    -1.33
    quo
    -1.33
    pinion
    -1.32
     nost
    -1.30
    refs
    -1.30
    POSITIVE LOGITS
    ities
    1.95
    opathology
    1.72
    itat
    1.67
    ités
    1.62
    tri
    1.58
    isation
    1.53
    trial
    1.51
    opathological
    1.51
    s
    1.50
    ization
    1.50
    Activations Density 0.043%

    No Known Activations