© 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 EvalsExportsinterp-engineNEWAPI 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. 25511
    Prev
    Next
    INDEX
    Explanations

    mentions of racing events or competitions

    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
    156
    +0.20
    1.2%
    376
    +0.15
    0.9%
    100
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.20
    0.01
    469
    +0.15
    0.01
    429
    +0.12
    0.01
    Negative Logits
    ĥ½
    -3.27
    ľĵ
    -2.42
    ħ
    -2.17
    ¿
    -2.08
    ¿½
    -2.06
    ķ
    -2.03
    Īĺ
    -2.02
    ↵↵
    -1.93
    -1.93
     ↵
    -1.93
    POSITIVE LOGITS
    craft
    1.66
     Awards
    1.61
     nominee
    1.56
    fruit
    1.51
    positions
    1.49
    AtIndex
    1.45
    ium
    1.44
    agne
    1.44
    doms
    1.41
    Script
    1.40
    Activations Density 0.015%

    No Known Activations