© 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. 30155
    Prev
    Next
    INDEX
    Explanations

    alcohol-related organizations and terminology

    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
    443
    +0.12
    0.7%
    369
    +0.11
    0.6%
    169
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    246
    +0.12
    0.02
    508
    +0.11
    0.02
    205
    +0.09
    0.02
    Negative Logits
     behaviour
    -1.76
    othelial
    -1.69
    oscopic
    -1.65
     suppose
    -1.64
    aturally
    -1.62
    ij
    -1.62
     autoimmune
    -1.60
    ĺ
    -1.57
    oscopy
    -1.55
     indeed
    -1.53
    POSITIVE LOGITS
    gart
    1.76
    way
    1.67
    gar
    1.67
    wood
    1.58
    gia
    1.58
    ureus
    1.55
    heet
    1.54
    gery
    1.51
    heads
    1.49
    head
    1.49
    Activations Density 0.179%

    No Known Activations