© 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. 30140
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures or treatments

    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
    +0.14
    0.9%
    474
    +0.14
    0.9%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.14
    0.01
    77
    +0.14
    0.01
    320
    +0.13
    0.00
    Negative Logits
    ĥ½
    -2.79
    Ĥ¬
    -2.29
    Ļª
    -2.18
    »
    -1.98
    IJ
    -1.96
    ľ
    -1.92
    ¼
    -1.89
    Ŀ
    -1.87
    ¾
    -1.87
    hood
    -1.81
    POSITIVE LOGITS
    eto
    1.89
     (@
    1.75
    blr
    1.74
    anese
    1.60
    etto
    1.54
    cine
    1.53
    \@
    1.50
    iper
    1.50
    istani
    1.50
    PW
    1.47
    Activations Density 0.009%

    No Known Activations