© 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. 29713
    Prev
    Next
    INDEX
    Explanations

    references to rules and regulations

    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
    +0.20
    1.2%
    156
    +0.18
    1.0%
    114
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.20
    0.03
    21
    +0.18
    0.02
    395
    +0.11
    0.02
    Negative Logits
    leans
    -1.82
    ---|---
    -1.80
    §
    -1.73
     dreams
    -1.72
    rophe
    -1.57
     Dreams
    -1.53
    |}
    -1.51
     NHS
    -1.50
    į
    -1.48
    sson
    -1.48
    POSITIVE LOGITS
    urgical
    1.82
    heet
    1.73
     ingredient
    1.67
    pot
    1.66
    etting
    1.63
    chool
    1.62
    burg
    1.62
    ume
    1.60
    path
    1.57
    icum
    1.56
    Activations Density 0.025%

    No Known Activations