© 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. 10865
    Prev
    Next
    INDEX
    Explanations

    phrases related to the conclusion of events or processes

    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
    263
    +0.13
    0.7%
    78
    +0.12
    0.6%
    481
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.04
    194
    +0.12
    0.03
    209
    +0.10
    0.04
    Negative Logits
    ŀ
    -4.96
    Ĵ
    -4.84
    ģ
    -4.76
    ľ
    -4.49
    Ŀ
    -4.47
    Ĥ
    -4.42
    ¢
    -4.40
    ¿
    -4.34
    ľĵ
    -4.27
    ¬
    -4.26
    POSITIVE LOGITS
     up
    2.36
     abruptly
    2.11
     disast
    2.10
     badly
    1.90
     premature
    1.88
    anger
    1.78
     shortly
    1.77
     infancy
    1.71
     innoc
    1.70
     happily
    1.65
    Activations Density 0.291%

    No Known Activations