© 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. 26910
    Prev
    Next
    INDEX
    Explanations

    references to significant wars and their associated terminology

    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
    156
    +0.18
    1.0%
    126
    +0.11
    0.6%
    294
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    486
    +0.18
    0.01
    89
    +0.11
    0.03
    293
    +0.11
    0.03
    Negative Logits
    plays
    -1.56
    sound
    -1.47
    win
    -1.37
    omitempty
    -1.35
    playing
    -1.33
     Directors
    -1.31
     history
    -1.30
    history
    -1.29
    bey
    -1.28
    ialize
    -1.27
    POSITIVE LOGITS
    edo
    1.80
    erie
    1.66
    ester
    1.53
     newsletter
    1.40
    ERC
    1.36
     rate
    1.36
    ERS
    1.36
    ique
    1.35
    edom
    1.31
     rat
    1.31
    Activations Density 0.386%

    No Known Activations