© 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. 2-RES-SM
    11. 13577
    Prev
    Next
    INDEX
    Explanations

    emotional expressions or reactions in narratives

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    464
    +0.14
    0.8%
    203
    +0.13
    0.7%
    171
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.14
    0.11
    171
    +0.13
    0.09
    135
    +0.12
    0.11
    Negative Logits
    obar
    -1.53
    ependence
    -1.44
     ordinary
    -1.38
    ulous
    -1.32
     ![](
    -1.32
    "}](#
    -1.29
     speeding
    -1.27
     calculation
    -1.27
    acity
    -1.26
     science
    -1.23
    POSITIVE LOGITS
    ¿
    2.19
    ŀ
    1.96
    ¾
    1.94
    ı
    1.93
    ¼
    1.92
    ĻĤ
    1.91
    IJ
    1.90
    ĺ
    1.83
    Ľ
    1.82
    s
    1.75
    Activations Density 0.415%

    No Known Activations