© 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. 0-MLP-SM
    11. 28637
    Prev
    Next
    INDEX
    Explanations

    references to individuals affected by crimes or traumatic events

    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
    +0.27
    1.7%
    376
    +0.13
    0.8%
    45
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.27
    0.02
    45
    +0.13
    0.02
    344
    +0.12
    0.02
    Negative Logits
    ĥ½
    -2.60
    ↵↵↵
    -2.38
     ↵
    -2.38
    ↵
    -2.38
    -2.38
    ↵  Âł
    -2.38
    č↵
    -2.38
    ↵
    -2.38
    ↵
    -2.38
    -2.38
    POSITIVE LOGITS
    cript
    2.02
    pace
    1.91
    hell
    1.90
    hip
    1.88
    uit
    1.76
    creen
    1.69
    ystems
    1.64
    pieces
    1.61
    piece
    1.59
    icum
    1.57
    Activations Density 0.039%

    No Known Activations