© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12194
    Prev
    Next
    INDEX
    Explanations

    references to family dynamics and relationships

    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
    387
    +0.13
    0.7%
    477
    +0.12
    0.7%
    476
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.13
    0.04
    313
    +0.12
    0.03
    387
    +0.11
    0.04
    Negative Logits
    ĥ½
    -5.16
    č↵
    -4.94
    ↵
    -4.94
    -4.94
    č↵
    -4.94
              ↵
    -4.94
    ↵
    -4.94
    -4.94
    -4.94
     ↵
    -4.94
    POSITIVE LOGITS
     members
    2.94
     member
    2.68
     reunion
    2.66
    members
    2.57
     resemblance
    2.29
     resem
    2.22
     affiliation
    2.19
     ties
    2.16
     crest
    2.00
     Members
    1.99
    Activations Density 0.326%

    No Known Activations