© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 27094
    Prev
    Next
    INDEX
    Explanations

    references to experiences and challenges in caregiving and child-rearing

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    350
    +0.12
    0.7%
    23
    +0.11
    0.6%
    135
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.12
    0.08
    239
    +0.11
    0.12
    147
    +0.10
    0.05
    Negative Logits
    deal
    -1.68
     experience
    -1.68
    etus
    -1.63
     Academy
    -1.57
     degrees
    -1.46
    ohan
    -1.45
     age
    -1.42
     discipline
    -1.42
    manship
    -1.41
    idea
    -1.41
    POSITIVE LOGITS
    ·
    2.54
    °
    2.49
    Ī
    2.47
    »
    2.45
    Īĺ
    2.44
    Ļª
    2.42
    ¶
    2.42
    Ĩ
    2.37
    ķ
    2.36
    ı
    2.34
    Activations Density 3.903%

    No Known Activations