© 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. 27070
    Prev
    Next
    INDEX
    Explanations

    references to performance metrics or measures

    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
    +0.26
    1.5%
    376
    +0.13
    0.7%
    72
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.26
    0.01
    203
    +0.13
    0.01
    56
    +0.10
    0.00
    Negative Logits
    ĵ
    -3.77
    §
    -3.72
    ĥ½
    -3.67
    <|outofrange|>
    -3.48
    č↵                   
    -3.48
     ↵     
    -3.48
    <|outofrange|>
    -3.48
    ↵↵                           
    -3.48
    ↵↵                               
    -3.48
    ↵↵                   
    -3.48
    POSITIVE LOGITS
    heet
    2.20
    hell
    1.68
    ium
    1.67
    et
    1.66
    quarters
    1.65
    point
    1.58
    ound
    1.57
    Pane
    1.57
    hole
    1.55
    ulator
    1.54
    Activations Density 3.151%

    No Known Activations