© 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. 29988
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "metrics."

    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
    425
    +0.13
    0.7%
    319
    +0.11
    0.6%
    285
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.13
    0.11
    371
    +0.11
    0.12
    18
    +0.11
    0.08
    Negative Logits
    lando
    -1.60
     reproduce
    -1.56
    mates
    -1.54
    ounger
    -1.53
    aten
    -1.51
    mate
    -1.50
     redistribute
    -1.43
     unl
    -1.42
     pose
    -1.41
    fecture
    -1.41
    POSITIVE LOGITS
    Script
    1.65
     Reference
    1.64
    reference
    1.46
    hani
    1.41
    javascript
    1.41
    Lists
    1.40
     References
    1.38
    forth
    1.37
     references
    1.32
    bone
    1.32
    Activations Density 0.204%

    No Known Activations