© 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. 1-RES-SM
    11. 25247
    Prev
    Next
    INDEX
    Explanations

    entities and organizations related to governance and societal structures

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.15
    0.9%
    278
    +0.14
    0.8%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.15
    0.06
    156
    +0.14
    0.08
    71
    +0.14
    0.08
    Negative Logits
    veis
    -1.61
    ubuntu
    -1.52
    erd
    -1.39
    80211
    -1.35
    enson
    -1.35
    tech
    -1.34
     että
    -1.31
    buntu
    -1.31
    "}](#
    -1.30
    astro
    -1.29
    POSITIVE LOGITS
    '?"
    1.50
    ---|---|---
    1.45
    ging
    1.44
    laughter
    1.44
    chers
    1.44
    nered
    1.43
    ization
    1.42
    pires
    1.39
     disgrace
    1.33
     scant
    1.33
    Activations Density 0.856%

    No Known Activations