© 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. 14181
    Prev
    Next
    INDEX
    Explanations

    references to a client

    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
    +0.24
    1.4%
    73
    +0.14
    0.8%
    365
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    80
    +0.24
    0.03
    73
    +0.14
    0.02
    173
    +0.14
    0.02
    Negative Logits
    utz
    -1.70
     dia
    -1.49
    ITION
    -1.44
     agarose
    -1.43
     mourning
    -1.41
     newborn
    -1.39
    assing
    -1.31
    rag
    -1.30
    itions
    -1.30
    aways
    -1.30
    POSITIVE LOGITS
    ele
    2.31
    het
    1.78
    stalk
    1.71
    istan
    1.66
    dom
    1.64
    client
    1.57
     services
    1.55
    HEL
    1.53
     service
    1.50
    flix
    1.49
    Activations Density 0.124%

    No Known Activations