© 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. 0-MLP-SM
    11. 28315
    Prev
    Next
    INDEX
    Explanations

    instances of the word "streaming" related to digital media or content delivery

    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
    +0.22
    1.3%
    376
    +0.13
    0.7%
    500
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.22
    0.01
    375
    +0.13
    0.01
    452
    +0.10
    0.01
    Negative Logits
    ľĵ
    -2.19
    ĥ½
    -2.11
    §
    -1.91
    Ŀ
    -1.84
    woke
    -1.75
    Į
    -1.71
    Ľ
    -1.61
    ľ
    -1.56
    rosse
    -1.56
    ½
    -1.50
    POSITIVE LOGITS
    gun
    1.93
    guns
    1.87
    apore
    1.87
    haus
    1.73
    iewicz
    1.60
    wise
    1.58
    ovich
    1.55
     instruments
    1.54
     prominently
    1.52
     instrument
    1.50
    Activations Density 0.011%

    No Known Activations