© 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. 1-RES-SM
    11. 29929
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of conditions or requirements

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    369
    +0.25
    1.4%
    151
    +0.15
    0.8%
    20
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.25
    0.07
    410
    +0.15
    0.10
    240
    +0.12
    0.00
    Negative Logits
    °
    -2.91
    ®
    -2.88
    ļ
    -2.64
    ½
    -2.61
    ij
    -2.54
    ĻĤ
    -2.52
    ¬
    -2.52
    £
    -2.45
    ľĵ
    -2.44
    Ģ
    -2.44
    POSITIVE LOGITS
    uckle
    1.50
    sel
    1.48
    bound
    1.41
     maiden
    1.35
    idegger
    1.34
     paras
    1.30
     Scotia
    1.30
    ÃŁ
    1.29
     unfolded
    1.27
    selves
    1.26
    Activations Density 1.435%

    No Known Activations