© 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 EvalsExportsAPI 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. 27548
    Prev
    Next
    INDEX
    Explanations

    terms related to serialization and normalizing data

    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
    +0.25
    1.5%
    73
    +0.10
    0.6%
    441
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    73
    +0.25
    0.03
    441
    +0.10
    0.01
    399
    +0.09
    0.02
    Negative Logits
     Cemetery
    -1.62
    >';
    -1.56
    tgz
    -1.53
     Esq
    -1.52
    reland
    -1.50
     HREF
    -1.49
     fain
    -1.44
    jours
    -1.43
     vain
    -1.42
    !'
    -1.42
    POSITIVE LOGITS
     governs
    1.74
     controls
    1.73
    volt
    1.69
    tes
    1.67
    guide
    1.66
     grip
    1.62
    ator
    1.61
     incorporates
    1.61
    ungs
    1.59
     contests
    1.59
    Activations Density 0.168%

    No Known Activations