© 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. 26704
    Prev
    Next
    INDEX
    Explanations

    references to the act of murder

    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
    156
    +0.21
    1.2%
    160
    +0.13
    0.7%
    116
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    116
    +0.21
    0.02
    160
    +0.13
    0.02
    204
    +0.11
    0.02
    Negative Logits
    ĥ½
    -3.25
    ķ
    -2.94
      ↵
    -2.72
    -2.72
    ↵↵
    -2.72
    ↵↵
    -2.72
    ↵↵
    -2.72
    ↵↵↵
    -2.72
     ↵
    -2.72
    -2.72
    POSITIVE LOGITS
     scenes
    2.07
    aic
    1.88
    ously
    1.87
    ous
    1.84
     era
    1.71
     scene
    1.60
    ingly
    1.57
    astic
    1.56
     exploits
    1.51
    igraph
    1.47
    Activations Density 0.044%

    No Known Activations