© 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. 29433
    Prev
    Next
    INDEX
    Explanations

    references to mechanical components related to motors

    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
    156
    +0.17
    1.0%
    376
    +0.15
    0.9%
    189
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.17
    0.01
    319
    +0.15
    0.00
    232
    +0.13
    0.00
    Negative Logits
    ĥ½
    -1.78
     Publ
    -1.60
     href
    -1.60
    ÑĢоÑģ
    -1.57
    ?’
    -1.57
    rowser
    -1.55
    orter
    -1.54
    ))?
    -1.48
    '?
    -1.46
    ção
    -1.44
    POSITIVE LOGITS
    craft
    1.94
    cock
    1.89
    oon
    1.70
    walk
    1.67
    ontal
    1.60
    fork
    1.58
    nut
    1.52
    wood
    1.52
    fors
    1.52
    face
    1.44
    Activations Density 0.005%

    No Known Activations