© 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. 26836
    Prev
    Next
    INDEX
    Explanations

    references to decreasing or minimizing various conditions or issues

    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
    2
    +0.14
    0.8%
    477
    +0.11
    0.6%
    457
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.14
    0.02
    120
    +0.11
    0.03
    475
    +0.10
    0.02
    Negative Logits
     overflow
    -1.50
     rinsed
    -1.49
     washed
    -1.42
     dotted
    -1.41
     pH
    -1.41
     wet
    -1.40
    uls
    -1.40
    aces
    -1.39
     spilled
    -1.38
     closed
    -1.37
    POSITIVE LOGITS
    ening
    1.83
    ↵
    1.75
    ↵
    1.75
    <|outofrange|>
    1.75
    <|outofrange|>
    1.75
    ↵Č
    1.75
    ↵
    1.75
    1.75
    ↵↵↵
    1.75
    1.75
    Activations Density 0.017%

    No Known Activations