© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 24530
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to ethical standards and principles

    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
    320
    +0.12
    0.7%
    2
    +0.12
    0.7%
    450
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    450
    +0.12
    0.03
    320
    +0.12
    0.02
    2
    +0.12
    0.03
    Negative Logits
    coming
    -1.72
    haul
    -1.64
    ching
    -1.63
    ched
    -1.62
    along
    -1.61
    endor
    -1.52
     sight
    -1.50
    cha
    -1.48
    shore
    -1.46
    atal
    -1.45
    POSITIVE LOGITS
    ¼
    2.09
    ī
    1.82
    ·
    1.79
    ¥
    1.74
    ĸ´
    1.71
     sake
    1.70
     rating
    1.67
    İ
    1.64
     requirements
    1.63
     committees
    1.63
    Activations Density 0.189%

    No Known Activations