© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26111
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and instruments, particularly in the context of esophageal or surgical interventions

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    23
    +0.18
    1.0%
    402
    +0.11
    0.6%
    73
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.18
    0.04
    458
    +0.11
    0.04
    276
    +0.11
    0.04
    Negative Logits
    Ļª
    -2.85
    »¿
    -2.74
    ī
    -2.72
    ĥ½
    -2.72
    ĩ
    -2.63
    ³
    -2.53
    Ħ
    -2.52
    Ľ
    -2.50
    Į
    -2.49
    ĻĤ
    -2.46
    POSITIVE LOGITS
     unfolding
    1.70
     clouds
    1.63
     devil
    1.54
     kernels
    1.52
     Writ
    1.51
     bread
    1.50
     crystals
    1.48
     sacred
    1.48
    rass
    1.47
     symbols
    1.47
    Activations Density 0.583%

    No Known Activations