© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24939
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "of" and its variations in both lowercase and uppercase

    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
    493
    +0.15
    0.9%
    156
    +0.15
    0.8%
    172
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    493
    +0.15
    0.02
    497
    +0.15
    0.00
    170
    +0.13
    0.02
    Negative Logits
    ictionary
    -1.68
    ivism
    -1.68
    ência
    -1.64
    iquity
    -1.52
    ):
    -1.51
    ivist
    -1.50
    ricular
    -1.48
    iotics
    -1.47
    ophage
    -1.47
    genstein
    -1.45
    POSITIVE LOGITS
    ľĵ
    3.11
    «
    2.95
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    2.89
    °
    2.84
    ↵↵
    2.81
     ↵
    2.81
    2.81
    2.81
    č↵
    2.81
     ↵
    2.81
    Activations Density 0.075%

    No Known Activations