© 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. 25498
    Prev
    Next
    INDEX
    Explanations

    references to various conferences and symposiums

    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
    376
    +0.16
    0.9%
    156
    +0.16
    0.9%
    412
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.16
    0.01
    398
    +0.16
    0.01
    416
    +0.13
    0.01
    Negative Logits
     reason
    -1.75
    abe
    -1.66
    ĥ½
    -1.61
     inflated
    -1.57
     git
    -1.56
    ---|---
    -1.46
     nature
    -1.45
    illed
    -1.41
    rian
    -1.38
     logged
    -1.38
    POSITIVE LOGITS
    smen
    1.74
     Center
    1.61
    ult
    1.58
    remia
    1.57
    head
    1.55
     Mush
    1.54
    taire
    1.50
     Square
    1.50
    fecture
    1.49
    itatively
    1.45
    Activations Density 0.017%

    No Known Activations