© 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. 4-RES-SM
    11. 13245
    Prev
    Next
    INDEX
    Explanations

    concepts related to emotional responses and interpersonal dynamics

    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
    21
    +0.30
    1.8%
    89
    +0.14
    0.8%
    186
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.30
    0.33
    156
    +0.14
    0.29
    71
    +0.12
    0.23
    Negative Logits
    ĻĤ
    -4.29
    Ļª
    -3.68
    £
    -3.54
    ¬
    -3.16
    Ń
    -3.15
    ľĵ
    -3.10
    ŀ
    -3.10
    ©
    -3.09
    ĥ½
    -3.08
    ĨĴ
    -3.07
    POSITIVE LOGITS
     they
    1.96
    they
    1.85
    their
    1.76
     mum
    1.67
    They
    1.67
     their
    1.66
     They
    1.64
    thems
    1.60
    Their
    1.57
     themselves
    1.52
    Activations Density 2.740%

    No Known Activations