© 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. 30788
    Prev
    Next
    INDEX
    Explanations

    emotions and their expressions

    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
    335
    +0.13
    0.7%
    317
    +0.13
    0.7%
    396
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.13
    0.04
    335
    +0.13
    0.04
    323
    +0.12
    0.02
    Negative Logits
    ¸
    -3.42
    Ģ
    -3.38
    ŀ
    -3.30
    ·¸
    -3.29
    į
    -3.28
    ¤
    -3.20
    ĥ
    -3.17
    ¿½
    -3.09
    ¯
    -3.07
    Ł
    -3.07
    POSITIVE LOGITS
    ingly
    1.65
    weight
    1.55
     towards
    1.54
     difference
    1.52
     ({
    1.51
    area
    1.49
     inside
    1.48
    ifiable
    1.47
    onte
    1.47
     pressure
    1.45
    Activations Density 0.184%

    No Known Activations