© 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. 27135
    Prev
    Next
    INDEX
    Explanations

    references to the term "Indian" in various contexts

    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
    132
    +0.14
    0.8%
    238
    +0.12
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.14
    0.02
    122
    +0.12
    0.02
    238
    +0.12
    0.02
    Negative Logits
     sudden
    -1.59
     latter
    -1.51
     true
    -1.50
     Trump
    -1.49
     typical
    -1.44
    yon
    -1.40
    astern
    -1.38
     result
    -1.37
     hyste
    -1.37
    ired
    -1.35
    POSITIVE LOGITS
    illac
    1.75
    ictionary
    1.72
    bour
    1.72
    leen
    1.69
    arms
    1.68
    ĻĤ
    1.66
    iples
    1.64
    bach
    1.64
    craft
    1.63
    onian
    1.63
    Activations Density 0.204%

    No Known Activations