© 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. 2-RES-SM
    11. 10854
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making processes and practices in various contexts

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    482
    +0.16
    0.9%
    418
    +0.13
    0.8%
    143
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.16
    -0.00
    365
    +0.13
    0.07
    141
    +0.11
    0.06
    Negative Logits
    ĻĤ
    -3.53
    ĸ´
    -3.38
    ¿
    -3.36
    ı
    -3.31
    Ľ
    -3.28
    ª
    -3.26
    ↵
    -3.20
    <|outofrange|>
    -3.20
    ↵
    -3.20
    -3.20
    POSITIVE LOGITS
     initiatives
    1.90
     goals
    1.88
    isms
    1.84
     aims
    1.72
     decisions
    1.72
     skills
    1.70
     strategies
    1.70
     committees
    1.69
    ically
    1.66
     capacity
    1.64
    Activations Density 1.244%

    No Known Activations