© 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. 26615
    Prev
    Next
    INDEX
    Explanations

    phrases related to health and wellness

    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
    291
    +0.14
    0.8%
    95
    +0.14
    0.8%
    272
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.14
    0.09
    95
    +0.14
    0.08
    272
    +0.13
    0.09
    Negative Logits
    Ĥ
    -1.98
    ¦
    -1.74
    Ļª
    -1.70
    ---|---|---
    -1.58
    rous
    -1.58
     ***
    -1.57
     Dev
    -1.55
    dess
    -1.53
     age
    -1.53
    ĩ
    -1.52
    POSITIVE LOGITS
    ashington
    1.54
    usalem
    1.46
     dialogue
    1.44
    igan
    1.39
     tribut
    1.39
    ipeg
    1.38
    lege
    1.37
    uria
    1.33
    bron
    1.32
     finances
    1.31
    Activations Density 1.065%

    No Known Activations