© 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. 24674
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to urgency and efficiency

    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
    198
    +0.15
    0.8%
    279
    +0.13
    0.7%
    342
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.15
    0.05
    86
    +0.13
    0.06
    145
    +0.12
    0.06
    Negative Logits
     suspicions
    -1.63
    ){#
    -1.51
     crate
    -1.49
    essen
    -1.48
     suspicion
    -1.46
    jours
    -1.40
    ']);
    -1.40
     unexpected
    -1.39
    inia
    -1.39
    ENRON
    -1.36
    POSITIVE LOGITS
    eler
    1.72
     though
    1.66
    uler
    1.48
    ucid
    1.47
    reflect
    1.43
     league
    1.41
     unto
    1.41
     insofar
    1.41
    matics
    1.40
    olite
    1.35
    Activations Density 0.776%

    No Known Activations