© 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. 9447
    Prev
    Next
    INDEX
    Explanations

    various expressions of emotional or affectionate sentiments

    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
    156
    +0.19
    1.1%
    410
    +0.18
    1.0%
    348
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.19
    0.06
    347
    +0.18
    0.07
    9
    +0.14
    0.04
    Negative Logits
    iable
    -1.53
     contraception
    -1.52
     infra
    -1.48
    documentclass
    -1.41
     resources
    -1.40
     resource
    -1.36
     """
    -1.35
     "
    -1.34
     earth
    -1.31
     percent
    -1.31
    POSITIVE LOGITS
    s
    3.72
    ll
    2.05
    teenth
    1.98
    si
    1.91
    eren
    1.91
    ller
    1.91
    tis
    1.87
    Ģ
    1.85
    lli
    1.83
    Connor
    1.82
    Activations Density 0.464%

    No Known Activations