© 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. 31003
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "cl" which likely refers to a specific coding or programming context

    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
    410
    +0.14
    0.8%
    172
    +0.13
    0.7%
    274
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.14
    0.03
    0
    +0.13
    0.03
    33
    +0.13
    0.03
    Negative Logits
    »¿
    -3.08
    ĩ
    -2.35
    ľĵ
    -2.14
    ¾
    -2.08
    ¿
    -2.07
    ĸ
    -1.99
    ↵
    -1.95
    ↵
    -1.95
    ↵
    -1.95
    ↵
    -1.95
    POSITIVE LOGITS
    otype
    1.73
    otypes
    1.57
    osure
    1.48
    otyping
    1.47
    osome
    1.41
     µM
    1.39
    odom
    1.38
    arity
    1.37
     ([
    1.35
     tested
    1.35
    Activations Density 1.818%

    No Known Activations