© 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. MLP Post
    9. 0-MLP-SM
    11. 28118
    Prev
    Next
    INDEX
    Explanations

    instances of the term "action" 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__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
    376
    +0.15
    0.9%
    336
    +0.13
    0.8%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    336
    +0.15
    0.02
    449
    +0.13
    0.02
    508
    +0.12
    0.01
    Negative Logits
     anything
    -1.78
    ]>
    -1.68
     her
    -1.63
     ?>
    -1.62
    ounder
    -1.59
     HREF
    -1.58
    )](#
    -1.57
     doing
    -1.51
     lonely
    -1.51
     BGCOLOR
    -1.51
    POSITIVE LOGITS
    naire
    2.85
    ist
    2.07
    nel
    2.02
    isters
    1.93
    ister
    1.86
    film
    1.83
    ismus
    1.82
    ism
    1.81
    ista
    1.80
    finder
    1.75
    Activations Density 0.018%

    No Known Activations