© 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. 25311
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fault" in various contexts, particularly related to legal or personal responsibility

    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
    274
    +0.14
    0.8%
    177
    +0.14
    0.8%
    371
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.14
    0.01
    274
    +0.14
    0.01
    429
    +0.13
    0.01
    Negative Logits
    thems
    -1.69
    itter
    -1.59
    then
    -1.52
    uther
    -1.49
    '>
    -1.43
    нÑı
    -1.42
     collapsed
    -1.38
     newspapers
    -1.37
     sudden
    -1.35
    eches
    -1.34
    POSITIVE LOGITS
    Ħ
    2.93
    ŀ
    2.91
    Ģ
    2.89
    Ł
    2.74
    £
    2.70
    ľĵ
    2.64
    º
    2.60
    ĻĤ
    2.58
    ¡
    2.52
    Ľ
    2.50
    Activations Density 0.018%

    No Known Activations