© 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. 0-MLP-SM
    6. 27797
    Prev
    Next
    INDEX
    Explanations

    references to meal-related content

    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
    +0.25
    1.5%
    93
    +0.11
    0.6%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.25
    0.01
    361
    +0.11
    0.01
    241
    +0.11
    0.01
    Negative Logits
    ĥ½
    -3.61
    <|outofrange|>
    -3.55
                                            
    -3.55
    <|outofrange|>
    -3.55
                                                           
    -3.55
    ↵               
    -3.55
    ↵↵                           
    -3.55
    <|outofrange|>
    -3.55
    č↵       
    -3.55
     ↵           
    -3.55
    POSITIVE LOGITS
    heet
    1.75
    ante
    1.74
    argument
    1.54
    nier
    1.50
    "};
    1.46
    uit
    1.46
    pun
    1.41
    ettle
    1.41
    etheless
    1.39
    print
    1.39
    Activations Density 0.021%

    No Known Activations