© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 26504
    Prev
    Next
    INDEX
    Explanations

    terms related to stress and its various manifestations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    365
    +0.12
    0.7%
    115
    +0.12
    0.7%
    319
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.12
    0.02
    422
    +0.12
    0.02
    273
    +0.11
    0.02
    Negative Logits
    µ
    -2.13
    ·¸
    -1.95
    ---|---|---
    -1.86
    ¾
    -1.86
    ¯
    -1.80
    ¸
    -1.76
    ¬
    -1.75
    atinib
    -1.71
    ¹
    -1.71
    ¿½
    -1.65
    POSITIVE LOGITS
     occasion
    2.09
     tolerance
    1.99
    ier
    1.82
    iest
    1.76
    ously
    1.74
    ingly
    1.59
     centers
    1.59
     occasions
    1.58
    igraphy
    1.58
     onset
    1.57
    Activations Density 0.299%

    No Known Activations