© 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. 25032
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements in Hertz and parts per million

    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
    120
    +0.13
    0.7%
    241
    +0.11
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    120
    +0.13
    0.01
    424
    +0.11
    0.01
    241
    +0.11
    0.01
    Negative Logits
    ĥ
    -3.58
    ¦
    -2.82
    ĥ½
    -2.78
    Ķ
    -2.76
    Ĥ
    -2.69
    ĵ
    -2.63
    »
    -2.60
    Ŀ
    -2.59
    ¿½
    -2.57
    ľĵ
    -2.57
    POSITIVE LOGITS
     platform
    1.90
    erals
    1.75
    istry
    1.75
     awa
    1.74
    bourne
    1.67
    stä
    1.64
    ART
    1.63
    ÅĽci
    1.59
     platforms
    1.52
    enos
    1.51
    Activations Density 0.016%

    No Known Activations