© 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. 2-MLP-SM
    11. 25192
    Prev
    Next
    INDEX
    Explanations

    references to gender, specifically mentions of male and female subjects

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    28
    +0.12
    0.7%
    97
    +0.12
    0.7%
    225
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.12
    0.01
    491
    +0.12
    0.01
    97
    +0.12
    0.01
    Negative Logits
    »¿
    -3.53
    Į
    -3.07
    ®
    -2.84
    ·¸
    -2.81
      ↵
    -2.80
    -2.80
    <|outofrange|>
    -2.80
    ↵
    -2.80
    č↵
    -2.80
    č↵
    -2.80
    POSITIVE LOGITS
    rils
    1.78
    ests
    1.57
     HERE
    1.54
     pictured
    1.53
     ðŁĻĤ
    1.49
     peek
    1.48
     ).
    1.45
     pictures
    1.41
    aspx
    1.39
    !).
    1.38
    Activations Density 0.091%

    No Known Activations