© 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. 25315
    Prev
    Next
    INDEX
    Explanations

    references to Japan

    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
    321
    +0.19
    1.1%
    227
    +0.17
    1.0%
    369
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.19
    0.03
    321
    +0.17
    0.03
    168
    +0.16
    0.02
    Negative Logits
    äsident
    -1.45
    abb
    -1.40
     decir
    -1.40
    cluding
    -1.37
     ich
    -1.34
     been
    -1.30
    tering
    -1.28
    qn
    -1.28
     Qt
    -1.28
     unspecified
    -1.27
    POSITIVE LOGITS
     themselves
    2.07
     herself
    1.90
     himself
    1.87
     itself
    1.86
    heet
    1.81
    ians
    1.77
    selves
    1.69
    cript
    1.65
    thems
    1.64
    himself
    1.60
    Activations Density 0.020%

    No Known Activations