© 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. 25809
    Prev
    Next
    INDEX
    Explanations

    references to emergency situations or 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
    503
    +0.14
    0.8%
    410
    +0.14
    0.8%
    240
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.14
    0.01
    510
    +0.14
    0.01
    239
    +0.12
    0.01
    Negative Logits
     same
    -1.55
    pite
    -1.52
     judgment
    -1.51
     commission
    -1.50
    eeper
    -1.49
    TRODUCTION
    -1.48
    orte
    -1.47
    atura
    -1.46
    "){
    -1.44
    Copyright
    -1.44
    POSITIVE LOGITS
    »
    3.31
    ¨
    3.17
    Ĵ
    2.94
    ½
    2.93
    ł
    2.87
    ±
    2.83
    ¡
    2.81
    ķ
    2.80
    ģ
    2.76
    µ
    2.70
    Activations Density 0.060%

    No Known Activations