© 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. 22613
    Prev
    Next
    INDEX
    Explanations

    the conjunction "but" indicating contrast in arguments or statements

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    76
    +0.16
    0.9%
    511
    +0.13
    0.7%
    160
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.16
    0.00
    225
    +0.13
    0.00
    274
    +0.13
    0.00
    Negative Logits
    thood
    -1.77
    arily
    -1.52
    rade
    -1.43
    inyl
    -1.39
     Edmonton
    -1.37
    eca
    -1.37
     relation
    -1.36
     \[
    -1.34
    ics
    -1.34
     requirements
    -1.33
    POSITIVE LOGITS
    Ľ
    4.19
    Ģ
    4.13
    Ī
    4.12
    ģ
    4.07
    Ĥ¬
    3.96
    «
    3.94
    Ħ
    3.85
    »
    3.83
    ĸ´
    3.83
    ¾
    3.82
    Activations Density 0.000%

    No Known Activations