© 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. 25046
    Prev
    Next
    INDEX
    Explanations

    references to prominent historical or influential figures

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    462
    +0.12
    0.7%
    87
    +0.11
    0.6%
    207
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.01
    462
    +0.11
    0.01
    107
    +0.11
    0.01
    Negative Logits
    '?"
    -2.17
    ?"
    -2.16
    ?'
    -2.12
    "?
    -2.11
     ?"
    -2.01
    ?_
    -1.98
    '?
    -1.88
    ·¸
    -1.74
    ?”
    -1.71
    "?"
    -1.66
    POSITIVE LOGITS
    journals
    1.82
    nutrition
    1.70
    framework
    1.69
     holdings
    1.66
    ÅĽci
    1.64
    mind
    1.63
    sdk
    1.58
     enjoyment
    1.52
    astro
    1.47
    ew
    1.44
    Activations Density 0.047%

    No Known Activations