© 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 EvalsExportsAPI 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. 29183
    Prev
    Next
    INDEX
    Explanations

    references to Japanese culture or the term 'Japanese' itself

    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
    71
    +0.13
    0.7%
    369
    +0.12
    0.7%
    321
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.13
    0.02
    71
    +0.12
    0.01
    423
    +0.12
    0.01
    Negative Logits
     measured
    -1.62
     monitored
    -1.53
     planned
    -1.44
     varying
    -1.38
     qui
    -1.36
     done
    -1.33
     quad
    -1.32
     imagin
    -1.29
     corresponding
    -1.29
     marked
    -1.29
    POSITIVE LOGITS
    cript
    1.94
    plain
    1.85
    ĻĤ
    1.69
    obe
    1.66
    oslov
    1.63
     Affairs
    1.62
    himself
    1.61
    lint
    1.58
    istani
    1.57
    thems
    1.56
    Activations Density 0.014%

    No Known Activations