© 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. 26816
    Prev
    Next
    INDEX
    Explanations

    references to the Phrygians in a historical or mythical context

    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
    410
    +0.15
    0.8%
    207
    +0.12
    0.7%
    388
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.15
    0.01
    207
    +0.12
    0.01
    111
    +0.12
    0.01
    Negative Logits
     ?"
    -1.74
     ?
    -1.51
     beard
    -1.48
     ")
    -1.46
    here
    -1.45
      ↵
    -1.45
    "));
    -1.44
    hin
    -1.42
    "];
    -1.40
    "))
    -1.39
    POSITIVE LOGITS
    £
    1.99
    ĥ½
    1.89
    ¨
    1.85
    Ľ
    1.85
    §
    1.81
    ³
    1.79
    kill
    1.68
    ¾
    1.62
    ©
    1.62
    µ
    1.61
    Activations Density 0.033%

    No Known Activations