© 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. 26777
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating statistical significance or results

    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
    369
    +0.16
    0.9%
    156
    +0.16
    0.9%
    308
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.16
    0.02
    290
    +0.16
    0.02
    106
    +0.14
    0.02
    Negative Logits
    eness
    -1.82
    river
    -1.73
     hazard
    -1.69
    iorari
    -1.61
    onia
    -1.55
    akia
    -1.52
    boarding
    -1.50
    iasis
    -1.47
    rition
    -1.45
    board
    -1.45
    POSITIVE LOGITS
    Ľ
    1.88
    ĭ
    1.74
    teen
    1.65
    ħ
    1.61
    ģ
    1.54
     percent
    1.50
    th
    1.49
    ĥ½
    1.44
    ffen
    1.44
    dB
    1.43
    Activations Density 0.020%

    No Known Activations