© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13551
    Prev
    Next
    INDEX
    Explanations

    mentions of generational terms related to demographic cohorts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    177
    +0.16
    0.9%
    386
    +0.15
    0.8%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.16
    0.02
    177
    +0.15
    0.03
    410
    +0.14
    0.02
    Negative Logits
    lando
    -1.74
    ://
    -1.62
    beit
    -1.54
    "])
    -1.50
     Redistributions
    -1.46
    ž
    -1.43
    legate
    -1.39
    ful
    -1.37
     precedent
    -1.37
    anut
    -1.37
    POSITIVE LOGITS
    ocide
    2.11
    etically
    1.82
    otypic
    1.76
    omics
    1.72
    eration
    1.58
    omic
    1.57
     consoles
    1.55
    etics
    1.55
    otoxicity
    1.49
    esp
    1.42
    Activations Density 0.102%

    No Known Activations