© 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. 11720
    Prev
    Next
    INDEX
    Explanations

    instances of loud, disruptive communication and emotional reactions

    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
    477
    +0.13
    0.8%
    432
    +0.13
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    432
    +0.13
    0.11
    417
    +0.13
    0.16
    477
    +0.12
    0.12
    Negative Logits
    ĥ½
    -4.14
    »¿
    -3.99
    ļ
    -3.92
    ľĵ
    -3.42
    ı
    -3.33
    IJ
    -3.30
    Īĺ
    -3.26
    ĸ
    -3.21
    ¶
    -3.18
    Ľ
    -3.18
    POSITIVE LOGITS
     remarks
    3.66
     comments
    3.22
     admon
    3.16
     remark
    3.15
     comment
    3.07
     applause
    3.06
     reply
    3.04
     aloud
    3.02
     loud
    3.00
     words
    2.93
    Activations Density 4.151%

    No Known Activations