© 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. 30391
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions

    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
    +0.25
    1.5%
    451
    +0.16
    0.9%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.25
    0.01
    273
    +0.16
    0.01
    301
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.91
    Ģ
    -2.74
    ĻĤ
    -2.59
    ¯
    -2.52
    Ļª
    -2.49
    ³
    -2.35
    ij
    -2.35
    §
    -2.32
    Ĵ
    -2.30
    ©
    -2.18
    POSITIVE LOGITS
    à±į
    1.92
    coin
    1.84
    àµį
    1.77
    à±ģ
    1.75
    àµ
    1.72
    pile
    1.70
    craft
    1.65
    horse
    1.62
    à±
    1.60
    à«ĩ
    1.58
    Activations Density 0.172%

    No Known Activations