© 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. 10863
    Prev
    Next
    INDEX
    Explanations

    references to relationships and familial connections

    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
    316
    +0.13
    0.7%
    447
    +0.13
    0.7%
    21
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.13
    0.10
    497
    +0.13
    0.05
    81
    +0.12
    0.06
    Negative Logits
    ↵            ↵
    -5.00
    ↵↵
    -5.00
    ↵
    -5.00
    -5.00
    ↵
    -5.00
    -5.00
    ↵
    -5.00
    -5.00
    ↵
    -5.00
    <|outofrange|>
    -5.00
    POSITIVE LOGITS
     friends
    3.02
     colleagues
    2.87
     own
    2.82
     peers
    2.81
     parents
    2.76
     wife
    2.68
     classmates
    2.67
     relatives
    2.62
     cousin
    2.61
     father
    2.56
    Activations Density 0.618%

    No Known Activations