© 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. 4-RES-SM
    11. 10387
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to auditory experiences and the act of listening

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    307
    +0.17
    1.0%
    306
    +0.16
    0.9%
    466
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.17
    0.04
    485
    +0.16
    0.03
    306
    +0.14
    0.03
    Negative Logits
    µ
    -2.68
    Ŀ
    -2.66
    Ľ
    -2.60
    ¼
    -2.59
    ½
    -2.55
    ľĵ
    -2.52
    ¤
    -2.51
    ĸ
    -2.49
    ¿½
    -2.42
    IJ
    -2.39
    POSITIVE LOGITS
     voices
    2.34
     about
    2.28
     whispers
    2.13
     rumors
    2.06
     stories
    2.03
     noises
    1.98
     aloud
    1.90
     testimon
    1.79
     murm
    1.75
     criticism
    1.75
    Activations Density 0.485%

    No Known Activations