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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25513
    Prev
    Next
    INDEX
    Explanations

    instances of the word "by"

    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
    356
    +0.15
    0.9%
    288
    +0.14
    0.8%
    54
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.15
    0.08
    362
    +0.14
    0.06
    496
    +0.13
    0.07
    Negative Logits
    olite
    -1.76
     simpler
    -1.60
     cloth
    -1.50
     manually
    -1.44
    ety
    -1.43
    hing
    -1.35
     nickname
    -1.32
     ÂĹ
    -1.30
     UPS
    -1.30
     mark
    -1.28
    POSITIVE LOGITS
    »¿
    2.52
     ↵
    2.44
    ↵↵
    2.44
              ↵
    2.44
    č↵
    2.44
    ↵  âĢĥ
    2.44
    ↵
    2.44
     ↵
    2.44
    ↵
    2.44
    2.44
    Activations Density 0.317%

    No Known Activations