© 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. 23200
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and identifiers related to scientific measurements and classifications

    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
    +0.21
    1.2%
    76
    +0.11
    0.6%
    374
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.21
    0.02
    298
    +0.11
    0.03
    159
    +0.11
    0.02
    Negative Logits
      ↵
    -5.28
    -5.28
    ↵
    -5.28
    ↵
    -5.28
             ↵
    -5.28
              ↵
    -5.28
    -5.28
    ↵
    -5.28
     ↵
    -5.28
    -5.28
    POSITIVE LOGITS
     Sunday
    1.54
     Christ
    1.44
     APPEALS
    1.44
     thereto
    1.41
    soon
    1.38
     annually
    1.36
    IBLE
    1.34
    oard
    1.33
    swick
    1.33
    ING
    1.32
    Activations Density 0.163%

    No Known Activations