© 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. 4-RES-SM
    11. 15220
    Prev
    Next
    INDEX
    Explanations

    terms related to testing and quality assurance in software development

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    139
    +0.15
    0.8%
    189
    +0.13
    0.7%
    50
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.15
    0.05
    211
    +0.13
    0.04
    349
    +0.12
    0.03
    Negative Logits
    OLOR
    -1.85
    roz
    -1.62
    reat
    -1.60
     owed
    -1.60
    ipple
    -1.60
    ilage
    -1.55
    ither
    -1.50
    alen
    -1.50
    agus
    -1.44
    christ
    -1.43
    POSITIVE LOGITS
    osterone
    3.42
    imony
    3.40
    imon
    3.19
    suite
    2.95
    ¾
    2.60
    ³
    2.51
    cases
    2.49
    ifies
    2.40
    case
    2.38
    Ī
    2.35
    Activations Density 0.388%

    No Known Activations