© 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. 28562
    Prev
    Next
    INDEX
    Explanations

    references to academic or educational hierarchy, specifically terms denoting levels like 'junior' and 'senior'

    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
    +0.16
    0.9%
    362
    +0.14
    0.8%
    457
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.06
    156
    +0.14
    0.04
    271
    +0.13
    0.01
    Negative Logits
    ĵ
    -3.18
    ¥
    -2.92
    Ĵ
    -2.83
    ı
    -2.80
    ³
    -2.76
    ĥ½
    -2.69
    ª
    -2.62
    ®
    -2.58
    ķ
    -2.53
    ²
    -2.51
    POSITIVE LOGITS
    ships
    2.21
    ity
    2.01
     rounds
    1.79
     citizens
    1.67
    arial
    1.65
     positions
    1.63
     citizen
    1.62
    iors
    1.58
    icum
    1.57
     quarters
    1.57
    Activations Density 0.349%

    No Known Activations