© 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. 30066
    Prev
    Next
    INDEX
    Explanations

    words related to importance or urgency, particularly in the context of priorities

    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
    +0.18
    1.0%
    30
    +0.10
    0.6%
    46
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.18
    0.02
    168
    +0.10
    0.02
    277
    +0.10
    0.01
    Negative Logits
    Ĵ
    -1.82
    ĥ½
    -1.82
    ľ
    -1.74
     moderate
    -1.70
    ±
    -1.66
    Ĥ¬
    -1.62
    ŀ
    -1.60
    »¿
    -1.55
    Ŀ
    -1.55
    ³
    -1.52
    POSITIVE LOGITS
    hole
    1.60
    ague
    1.56
    bow
    1.56
    fix
    1.52
    ita
    1.48
    osa
    1.48
     plaque
    1.47
    etting
    1.45
     duties
    1.43
    ilage
    1.42
    Activations Density 0.586%

    No Known Activations