© 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. 31072
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and emotional responses

    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
    332
    +0.13
    0.7%
    349
    +0.11
    0.6%
    459
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.13
    0.55
    56
    +0.11
    0.11
    23
    +0.11
    0.42
    Negative Logits
     triv
    -1.60
     positively
    -1.51
     hol
    -1.45
    ensen
    -1.44
    MIT
    -1.37
     loved
    -1.34
    acy
    -1.34
    iveau
    -1.33
    orial
    -1.32
    \][
    -1.32
    POSITIVE LOGITS
    osus
    1.80
    hores
    1.54
    uch
    1.53
    thia
    1.52
    eg
    1.51
     ["
    1.48
     Reporting
    1.48
    urus
    1.47
    ube
    1.46
    kowski
    1.44
    Activations Density 5.199%

    No Known Activations