© 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. 30005
    Prev
    Next
    INDEX
    Explanations

    references to air conditioning

    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
    376
    +0.13
    0.8%
    217
    +0.11
    0.7%
    235
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.13
    0.05
    56
    +0.11
    0.02
    203
    +0.10
    0.04
    Negative Logits
    ¯
    -4.50
    ĥ½
    -4.46
    ²
    -4.08
    ĨĴ
    -4.07
    Ŀ
    -4.03
    ±
    -3.99
    ĸ´
    -3.96
    į
    -3.88
    ľ
    -3.85
    ĸ
    -3.84
    POSITIVE LOGITS
     oven
    1.71
     apparatus
    1.67
     chambers
    1.57
     equipment
    1.54
     setup
    1.53
     regime
    1.52
    unit
    1.49
     crop
    1.49
     cavity
    1.48
     schedules
    1.48
    Activations Density 3.588%

    No Known Activations