© 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. 2-MLP-SM
    11. 26696
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to medical emergencies and disasters

    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
    121
    +0.22
    1.2%
    156
    +0.17
    1.0%
    39
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.22
    0.05
    39
    +0.17
    0.03
    23
    +0.15
    0.04
    Negative Logits
    inous
    -1.65
    ulp
    -1.65
    ável
    -1.64
    hui
    -1.62
    itarian
    -1.59
    quet
    -1.58
    iral
    -1.56
    oid
    -1.56
    pad
    -1.54
    izo
    -1.53
    POSITIVE LOGITS
     emphasis
    1.93
     appreciation
    1.71
    ħ
    1.70
    ths
    1.66
    Ĥ
    1.57
    OUGH
    1.54
     masters
    1.50
     homeland
    1.50
     compositions
    1.48
     producers
    1.48
    Activations Density 1.766%

    No Known Activations