© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22694
    Prev
    Next
    INDEX
    Explanations

    words related to national and cultural identities

    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
    470
    +0.14
    0.8%
    148
    +0.11
    0.6%
    225
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.14
    0.04
    344
    +0.11
    0.06
    148
    +0.11
    0.04
    Negative Logits
     rival
    -1.60
    ment
    -1.55
    cher
    -1.48
    ropolis
    -1.45
     figures
    -1.43
    quart
    -1.42
    nier
    -1.41
     contre
    -1.39
     initiatives
    -1.39
    ctrine
    -1.39
    POSITIVE LOGITS
    ĥ½
    2.40
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    1.89
    »¿
    1.72
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    1.57
    iseconds
    1.54
     ears
    1.52
    ÃĥÃĤÃĥÃĤ
    1.51
     inbox
    1.49
    dB
    1.48
    isciplinary
    1.46
    Activations Density 0.434%

    No Known Activations