© 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. 28998
    Prev
    Next
    INDEX
    Explanations

    concepts related to mindfulness and health

    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
    +0.37
    2.3%
    148
    +0.14
    0.8%
    219
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.37
    0.01
    80
    +0.14
    0.01
    173
    +0.09
    0.01
    Negative Logits
    že
    -1.77
    ţ
    -1.52
    ção
    -1.43
    ificantly
    -1.43
    ções
    -1.35
     vaccinated
    -1.34
     yours
    -1.30
    ţi
    -1.28
    «
    -1.28
    ene
    -1.28
    POSITIVE LOGITS
    µ
    1.57
    ¨
    1.40
    strand
    1.39
    £
    1.34
    iss
    1.32
    casters
    1.31
     relativity
    1.29
    mission
    1.29
    ²
    1.29
     positions
    1.28
    Activations Density 0.005%

    No Known Activations