© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25557
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals or events related to sports

    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
    506
    +0.12
    0.7%
    329
    +0.12
    0.6%
    61
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    61
    +0.12
    0.10
    86
    +0.12
    0.04
    329
    +0.11
    0.01
    Negative Logits
     backing
    -1.70
    TOD
    -1.67
     messaging
    -1.65
     gamers
    -1.61
    }</
    -1.60
     twe
    -1.56
     pandas
    -1.51
     chunk
    -1.51
     namespace
    -1.51
     legacy
    -1.49
    POSITIVE LOGITS
    Ģ
    4.78
    »¿
    4.50
    ĻĤ
    4.49
    º
    4.46
    Ħ
    4.36
    ĥ
    4.34
    ij
    4.34
    Ĭ
    4.30
    ¯
    4.29
    ª
    4.22
    Activations Density 3.807%

    No Known Activations