© 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. 2-MLP-SM
    11. 23728
    Prev
    Next
    INDEX
    Explanations

    mentions of specific years and data references related to economic and social trends

    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/2-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.2.hook_mlp_out
    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
    159
    +0.13
    0.7%
    394
    +0.12
    0.7%
    335
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.13
    0.16
    394
    +0.12
    0.17
    493
    +0.12
    0.12
    Negative Logits
     smiled
    -1.75
     laughed
    -1.70
     assured
    -1.68
     reminded
    -1.67
     sighed
    -1.67
     shrugged
    -1.65
     calmly
    -1.61
     chuckled
    -1.61
     grinned
    -1.59
     simply
    -1.53
    POSITIVE LOGITS
    orem
    1.72
    ift
    1.66
    otec
    1.52
    license
    1.49
    amous
    1.41
    enses
    1.41
    ÅĤy
    1.41
    omen
    1.39
    ale
    1.38
    refs
    1.38
    Activations Density 6.112%

    No Known Activations