© 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. 2-MLP-SM
    11. 23265
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to scientific terms and measurements

    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
    156
    +0.38
    2.2%
    23
    +0.21
    1.2%
    31
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.38
    0.04
    491
    +0.21
    0.05
    374
    +0.12
    0.02
    Negative Logits
    »
    -1.86
    ↵↵
    -1.71
    -1.71
    č↵
    -1.71
    č↵
    -1.71
    ↵
    -1.71
    ↵
    -1.71
    ↵↵
    -1.71
    -1.71
    ↵
    -1.71
    POSITIVE LOGITS
    TRODUCTION
    1.43
     invention
    1.43
     beginnings
    1.39
    [(
    1.37
     caution
    1.27
    (_
    1.25
     infer
    1.25
     nickname
    1.24
     initial
    1.22
     mang
    1.22
    Activations Density 0.470%

    No Known Activations