© 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. 30102
    Prev
    Next
    INDEX
    Explanations

    references to context, particularly in relation to various subjects or evidence presented

    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
    365
    +0.11
    0.6%
    184
    +0.11
    0.6%
    504
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.11
    0.02
    28
    +0.11
    0.02
    504
    +0.11
    0.02
    Negative Logits
    ĥ½
    -2.62
    §
    -2.58
    ¾
    -2.55
    ĻĤ
    -2.54
     ↵
    -2.44
    -2.44
    ↵
    -2.44
    ↵
    -2.44
     ↵
    -2.44
    -2.44
    POSITIVE LOGITS
     menu
    2.08
    inally
    1.83
    ually
    1.80
    HEL
    1.71
     menus
    1.65
    ily
    1.65
    ual
    1.64
    ier
    1.62
     perspective
    1.61
    ivated
    1.61
    Activations Density 0.074%

    No Known Activations