© 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 EvalsExportsAPI 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. 28521
    Prev
    Next
    INDEX
    Explanations

    references to prenatal care

    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
    +0.23
    1.4%
    148
    +0.14
    0.8%
    30
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.23
    0.01
    156
    +0.14
    0.01
    71
    +0.11
    0.01
    Negative Logits
    ween
    -1.57
    vester
    -1.52
    ahu
    -1.51
    ders
    -1.46
    agles
    -1.45
    croft
    -1.37
    romy
    -1.35
     publish
    -1.34
     Columb
    -1.33
     stratified
    -1.32
    POSITIVE LOGITS
    "}](#
    1.98
    Ģ
    1.91
    ģ
    1.74
    ĻĤ
    1.73
     pains
    1.71
    ¿½
    1.60
    ľĵ
    1.52
    º
    1.47
    ł
    1.46
    ¤
    1.46
    Activations Density 0.009%

    No Known Activations