© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24960
    Prev
    Next
    INDEX
    Explanations

    the word "arrived" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.19
    1.1%
    148
    +0.15
    0.9%
    115
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.19
    0.02
    137
    +0.15
    0.02
    347
    +0.15
    0.02
    Negative Logits
    writing
    -1.63
    icin
    -1.59
    ized
    -1.45
    fered
    -1.45
    developed
    -1.42
    orter
    -1.38
    icular
    -1.38
    ink
    -1.36
    awed
    -1.36
    ked
    -1.35
    POSITIVE LOGITS
     Minn
    1.61
    ulses
    1.50
    émon
    1.46
    enti
    1.45
    entes
    1.40
    ensibly
    1.39
    ensible
    1.39
     Majesty
    1.38
    atri
    1.37
    rien
    1.36
    Activations Density 0.025%

    No Known Activations