© 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. 25298
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the same individual, indicated by the recurring activation of the name "JR."

    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
    412
    +0.16
    0.9%
    376
    +0.14
    0.8%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    412
    +0.16
    0.01
    105
    +0.14
    0.01
    319
    +0.12
    0.01
    Negative Logits
     '</
    -1.93
    itoring
    -1.44
    uality
    -1.43
    amethasone
    -1.43
    reporting
    -1.42
    thren
    -1.41
    alus
    -1.40
     him
    -1.39
     clinically
    -1.38
     attendant
    -1.36
    POSITIVE LOGITS
    ®
    2.45
    ¹
    2.28
    £
    2.18
    ļ
    2.18
    ª
    2.14
    ½
    2.10
    PG
    2.04
    ¤
    2.03
    º
    2.00
    ´
    1.91
    Activations Density 0.010%

    No Known Activations