© 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. 0-MLP-SM
    11. 25671
    Prev
    Next
    INDEX
    Explanations

    repeated phrases indicating a sense of ownership or possession

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    380
    +0.13
    0.7%
    108
    +0.12
    0.7%
    178
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    338
    +0.13
    0.03
    1
    +0.12
    0.03
    506
    +0.12
    0.02
    Negative Logits
    ido
    -1.54
    once
    -1.50
    ai
    -1.48
    anged
    -1.48
    esse
    -1.45
     you
    -1.43
    ás
    -1.39
     ok
    -1.38
    outer
    -1.38
    um
    -1.37
    POSITIVE LOGITS
    ↵
    2.34
    2.34
    ↵
    2.34
    2.34
    2.34
      ↵
    2.34
    ↵↵↵
    2.34
    2.34
        ↵
    2.34
    č↵č↵
    2.34
    Activations Density 0.008%

    No Known Activations