© 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. 25043
    Prev
    Next
    INDEX
    Explanations

    the word "this" in various contexts

    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
    491
    +0.14
    0.8%
    478
    +0.12
    0.7%
    407
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.14
    0.15
    26
    +0.12
    0.14
    199
    +0.11
    0.14
    Negative Logits
    boro
    -1.55
     flock
    -1.44
     Observatory
    -1.43
     anode
    -1.40
    helf
    -1.40
    ERN
    -1.30
    heid
    -1.30
    вÑĢ
    -1.29
    NAP
    -1.27
     Zoo
    -1.26
    POSITIVE LOGITS
    Ļª
    2.10
    º
    1.93
    Ģ
    1.92
    ĥ
    1.92
    etted
    1.76
    fered
    1.71
    ¦
    1.66
     dont
    1.65
    ¼
    1.61
    İ
    1.61
    Activations Density 0.273%

    No Known Activations