© 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. 30989
    Prev
    Next
    INDEX
    Explanations

    conditional statements and expressions of possibilities

    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
    144
    +0.13
    0.7%
    202
    +0.13
    0.7%
    233
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.13
    0.11
    233
    +0.13
    0.10
    486
    +0.11
    0.09
    Negative Logits
     checks
    -1.90
    ¡
    -1.73
    icum
    -1.72
    ĻĤ
    -1.70
    ı
    -1.70
    ½
    -1.67
    Ľ
    -1.65
    ľĵ
    -1.62
    gered
    -1.60
     therein
    -1.56
    POSITIVE LOGITS
    iox
    1.47
    uvre
    1.44
    riel
    1.40
    vic
    1.40
     deceased
    1.39
    zia
    1.37
    iam
    1.36
     genus
    1.34
    ago
    1.34
    zi
    1.33
    Activations Density 0.344%

    No Known Activations