© 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. 27919
    Prev
    Next
    INDEX
    Explanations

    references to particles and nanoparticle-related concepts

    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
    502
    +0.17
    1.0%
    156
    +0.14
    0.8%
    232
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.17
    0.01
    102
    +0.14
    0.01
    232
    +0.12
    0.01
    Negative Logits
    Ń
    -2.92
    ·
    -2.42
    ³
    -2.32
    ĥ½
    -2.29
    ½
    -2.21
    §
    -2.16
    Ŀ
    -2.14
    ´
    -2.12
    ·¸
    -2.11
    ¶
    -2.10
    POSITIVE LOGITS
    nikov
    1.74
    burst
    1.65
    ni
    1.61
    finder
    1.60
    ics
    1.59
    scar
    1.57
    less
    1.57
    folio
    1.57
    obi
    1.56
    pora
    1.56
    Activations Density 0.005%

    No Known Activations