© 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. 26996
    Prev
    Next
    INDEX
    Explanations

    mentions of "Google"

    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
    369
    +0.18
    1.1%
    71
    +0.14
    0.8%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.18
    0.04
    332
    +0.14
    0.03
    71
    +0.14
    0.03
    Negative Logits
     possible
    -1.59
    woke
    -1.59
     saline
    -1.49
     male
    -1.49
     pregnant
    -1.47
     pure
    -1.45
     promise
    -1.41
    idem
    -1.41
     lethal
    -1.41
     median
    -1.41
    POSITIVE LOGITS
    fors
    1.82
    burn
    1.70
    ings
    1.70
    yards
    1.70
    bard
    1.66
    craft
    1.65
    fonts
    1.57
    film
    1.54
    films
    1.53
    wood
    1.52
    Activations Density 0.045%

    No Known Activations