© 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. 30850
    Prev
    Next
    INDEX
    Explanations

    references to specific products or branding associated with health and fitness

    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
    +0.21
    1.2%
    376
    +0.14
    0.8%
    392
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.21
    0.01
    392
    +0.14
    0.01
    347
    +0.14
    0.01
    Negative Logits
     its
    -1.72
     child
    -1.64
     marital
    -1.63
     spouse
    -1.54
     fair
    -1.52
    woke
    -1.51
    acial
    -1.41
     unlawful
    -1.41
     protected
    -1.41
     birth
    -1.38
    POSITIVE LOGITS
    £
    2.10
    °
    1.98
    ¿½
    1.94
    ¼
    1.94
    bow
    1.81
    erals
    1.79
    Īĺ
    1.76
    ¢
    1.70
    ¬
    1.68
    liga
    1.67
    Activations Density 0.009%

    No Known Activations