© 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. 23351
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentions and aims 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/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
    500
    +0.15
    0.8%
    135
    +0.12
    0.6%
    105
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.15
    0.03
    94
    +0.12
    0.05
    122
    +0.11
    0.02
    Negative Logits
     brackets
    -1.41
    )—
    -1.41
    .^[@
    -1.36
     letters
    -1.35
    lists
    -1.35
    izione
    -1.33
     unfamiliar
    -1.32
     appointed
    -1.29
     occasion
    -1.29
    âĢIJ
    -1.29
    POSITIVE LOGITS
    ĥ½
    1.97
              ↵
    1.95
    ↵
    1.95
    ↵
    1.95
    ↵
    1.95
    ↵
    1.95
    ↵
    1.95
    ↵
    1.95
     ↵
    1.95
    ↵
    1.95
    Activations Density 0.894%

    No Known Activations