© 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. 26112
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering and machinery

    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
    478
    +0.14
    0.8%
    240
    +0.12
    0.7%
    302
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.14
    0.03
    418
    +0.12
    -0.00
    390
    +0.12
    0.01
    Negative Logits
    aceous
    -1.74
    istry
    -1.59
     Rptr
    -1.56
     reps
    -1.41
     skills
    -1.39
    bie
    -1.39
    esque
    -1.37
     inches
    -1.36
     heels
    -1.36
     himself
    -1.35
    POSITIVE LOGITS
    TRODUCTION
    1.64
    ôle
    1.58
    existence
    1.56
    said
    1.49
    âĢĤ
    1.45
     Invention
    1.44
    ============
    1.43
     widespread
    1.40
     Fifth
    1.32
     indebted
    1.31
    Activations Density 0.083%

    No Known Activations