© 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. 29437
    Prev
    Next
    INDEX
    Explanations

    references to military or governmental forces

    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
    376
    +0.15
    0.9%
    217
    +0.12
    0.7%
    145
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.15
    0.02
    275
    +0.12
    0.02
    217
    +0.12
    0.01
    Negative Logits
     gay
    -1.80
    hes
    -1.61
     fellow
    -1.58
     nephew
    -1.56
     homosexual
    -1.55
     Christ
    -1.55
     chance
    -1.54
    idem
    -1.53
     friends
    -1.52
     horrible
    -1.51
    POSITIVE LOGITS
    «
    3.71
    ¥
    3.61
    ģ
    3.59
    Ī
    3.51
    Ļ
    3.44
    ¿½
    3.36
    ī
    3.34
    ĸ
    3.34
    ®
    3.31
    ļ
    3.31
    Activations Density 0.007%

    No Known Activations