© 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. 27953
    Prev
    Next
    INDEX
    Explanations

    the name "United" in various contexts

    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
    417
    +0.11
    0.6%
    71
    +0.10
    0.6%
    150
    +0.09
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.11
    0.01
    150
    +0.10
    0.01
    187
    +0.09
    0.01
    Negative Logits
    ,'"
    -1.58
     abnormal
    -1.55
     full
    -1.54
     shame
    -1.53
    \)
    -1.53
    '),
    -1.53
     crashing
    -1.51
     mocking
    -1.50
    '))
    -1.48
    "`
    -1.48
    POSITIVE LOGITS
    ÅĽci
    2.06
    à±į
    1.93
    àµį
    1.92
    rooms
    1.89
    á̏
    1.88
    ↵                                               
    1.86
    ↵                
    1.86
                                               
    1.86
    ↵↵    
    1.86
    č↵                   
    1.86
    Activations Density 0.007%

    No Known Activations