© 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. 25726
    Prev
    Next
    INDEX
    Explanations

    words that indicate discovering or locating something

    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
    348
    +0.13
    0.7%
    293
    +0.11
    0.6%
    464
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    118
    +0.13
    0.05
    496
    +0.11
    0.05
    320
    +0.11
    0.04
    Negative Logits
    ighting
    -1.75
    seeing
    -1.59
    ORD
    -1.57
     invas
    -1.53
    idity
    -1.50
     presence
    -1.49
    versal
    -1.45
     Philippines
    -1.44
    tering
    -1.44
    Saharan
    -1.41
    POSITIVE LOGITS
    oint
    1.62
    oted
    1.51
     appointed
    1.49
    arat
    1.47
    ugin
    1.40
     established
    1.39
     author
    1.38
     repe
    1.38
     recharge
    1.37
    nae
    1.35
    Activations Density 0.032%

    No Known Activations