© 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. 26086
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to treatments, supplements, and physical therapy

    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
    145
    +0.14
    0.8%
    156
    +0.12
    0.7%
    194
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    37
    +0.14
    0.03
    410
    +0.12
    0.02
    433
    +0.11
    0.03
    Negative Logits
     defects
    -1.86
    İ
    -1.84
    ocytes
    -1.72
    ĵ
    -1.71
    į
    -1.66
    Į
    -1.57
    ı
    -1.57
    ij
    -1.56
     resemble
    -1.54
     dysplasia
    -1.49
    POSITIVE LOGITS
     **
    1.69
    hower
    1.53
     **_
    1.50
    shots
    1.46
     cycle
    1.45
    fuel
    1.45
     Administration
    1.44
     rains
    1.43
    cock
    1.38
     bush
    1.37
    Activations Density 1.090%

    No Known Activations