© 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. 29893
    Prev
    Next
    INDEX
    Explanations

    references to Brazilian culture or identity

    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
    +0.13
    0.7%
    71
    +0.13
    0.7%
    182
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.04
    434
    +0.13
    0.03
    151
    +0.12
    0.03
    Negative Logits
    ĥ½
    -1.84
      ↵
    -1.55
     different
    -1.52
    ¶
    -1.52
     Trump
    -1.50
    opsy
    -1.48
     sudden
    -1.48
    erson
    -1.47
     unintended
    -1.39
    hr
    -1.37
    POSITIVE LOGITS
    smen
    1.84
     defenses
    1.76
    fires
    1.71
    als
    1.66
    istically
    1.65
    istan
    1.61
    cias
    1.59
    framework
    1.59
    ate
    1.57
    \]-
    1.56
    Activations Density 2.154%

    No Known Activations