© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 26928
    Prev
    Next
    INDEX
    Explanations

    references to cuteness or adorable qualities in descriptions

    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
    +0.41
    2.5%
    376
    +0.16
    1.0%
    148
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.41
    0.02
    74
    +0.16
    0.02
    466
    +0.15
    0.02
    Negative Logits
     ↵
    -1.67
    ↵
    -1.67
    -1.67
    č↵
    -1.67
    ↵
    -1.67
     ↵
    -1.67
    ↵↵
    -1.67
    -1.67
    ↵
    -1.67
    -1.67
    POSITIVE LOGITS
    like
    1.78
     enough
    1.68
    "}](#
    1.52
    edly
    1.48
    tagged
    1.47
    fellow
    1.43
     coupled
    1.42
    rant
    1.39
    ulate
    1.37
    gered
    1.35
    Activations Density 0.041%

    No Known Activations