© 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. 31739
    Prev
    Next
    INDEX
    Explanations

    emotions and expressions of struggle

    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
    263
    +0.24
    1.4%
    419
    +0.20
    1.1%
    231
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.24
    0.08
    358
    +0.20
    0.06
    419
    +0.14
    0.04
    Negative Logits
    hores
    -1.62
    eks
    -1.44
    imon
    -1.38
     strategies
    -1.33
    à°¿
    -1.32
     hypot
    -1.30
     prisoner
    -1.29
    kinase
    -1.29
    chel
    -1.29
    hered
    -1.29
    POSITIVE LOGITS
     anymore
    2.26
     anybody
    1.78
     ever
    1.70
     whatsoever
    1.67
     anything
    1.63
     enough
    1.60
    webkit
    1.59
     minded
    1.53
     fancy
    1.49
    athom
    1.48
    Activations Density 0.471%

    No Known Activations