© 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. 29422
    Prev
    Next
    INDEX
    Explanations

    instances of the word "I" indicating first-person expressions and perspectives

    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
    369
    +0.18
    1.0%
    71
    +0.13
    0.7%
    171
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.18
    0.17
    242
    +0.13
    0.17
    299
    +0.12
    0.16
    Negative Logits
    ľĵ
    -1.94
    ://
    -1.89
    ↵
    -1.89
    -1.89
    č↵
    -1.89
    -1.89
    ↵  ³³³
    -1.89
    ↵
    -1.89
    ↵
    -1.89
    -1.89
    POSITIVE LOGITS
    brahim
    2.10
    bn
    1.89
     conjecture
    1.83
    NdEx
    1.78
    Enumerable
    1.62
    ago
    1.62
    stanbul
    1.62
    ANS
    1.61
    cción
    1.61
    ${
    1.57
    Activations Density 7.934%

    No Known Activations