© 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. 0-MLP-SM
    11. 30928
    Prev
    Next
    INDEX
    Explanations

    terms related to anthropology

    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
    87
    +0.14
    0.8%
    501
    +0.14
    0.8%
    325
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.14
    0.01
    87
    +0.14
    0.01
    325
    +0.11
    0.01
    Negative Logits
    Ļª
    -2.23
     same
    -1.85
    hin
    -1.46
     possible
    -1.40
     afternoon
    -1.39
     fatal
    -1.38
     abort
    -1.35
     theirs
    -1.33
    consin
    -1.32
    áĢ¯
    -1.29
    POSITIVE LOGITS
    omorphism
    1.77
    omorphic
    1.65
    ilee
    1.62
    like
    1.60
    ologist
    1.55
    ist
    1.55
    odynam
    1.49
    enhanced
    1.48
     posed
    1.48
    it
    1.47
    Activations Density 0.006%

    No Known Activations