© 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. 26996
    Prev
    Next
    INDEX
    Explanations

    references to prestigious institutions and organizations

    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
    +0.17
    0.9%
    446
    +0.13
    0.7%
    83
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.17
    0.09
    446
    +0.13
    0.04
    23
    +0.13
    0.05
    Negative Logits
    inted
    -1.63
    izon
    -1.61
    ondon
    -1.60
    .
    -1.59
    ../../
    -1.57
    аÑħ
    -1.57
    :"){
    -1.51
    onate
    -1.48
    iph
    -1.45
    /
    -1.43
    POSITIVE LOGITS
    ¦
    3.44
    Ļª
    3.07
    ²
    2.90
    «
    2.90
    Īĺ
    2.88
    Į
    2.85
    ¤
    2.82
    Ĭ
    2.82
    Ĺ
    2.80
    ¢
    2.78
    Activations Density 1.346%

    No Known Activations