© 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. 2-MLP-SM
    6. 26665
    Prev
    Next
    INDEX
    Explanations

    instructions related to user interface interactions and layout adjustments

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    418
    +0.12
    0.6%
    66
    +0.11
    0.6%
    74
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.12
    0.04
    38
    +0.11
    0.00
    187
    +0.11
    0.01
    Negative Logits
    Ľ
    -2.71
    Īĺ
    -2.70
    ľĵ
    -2.64
    ĥ½
    -2.45
    ¢
    -2.38
    Ł
    -2.38
    ħ
    -2.37
    į
    -2.36
    ↵↵                                
    -2.34
    ↵↵           
    -2.34
    POSITIVE LOGITS
    hest
    1.62
     nineteenth
    1.53
     inquiry
    1.50
     widespread
    1.44
     Ontario
    1.42
     spokesman
    1.39
     Ages
    1.38
     theatre
    1.38
     climate
    1.37
    agogue
    1.36
    Activations Density 1.069%

    No Known Activations