© 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. 31058
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their frequency

    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
    110
    +0.13
    0.7%
    422
    +0.12
    0.7%
    22
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.13
    0.36
    23
    +0.12
    0.31
    494
    +0.12
    0.25
    Negative Logits
    ests
    -1.81
    ances
    -1.74
    ital
    -1.69
     thereof
    -1.59
    isions
    -1.54
    endar
    -1.51
    aeda
    -1.49
     Somalia
    -1.45
    ongo
    -1.44
    aea
    -1.42
    POSITIVE LOGITS
    Į
    2.98
    ij
    2.74
    ĥ½
    2.49
    ĻĤ
    2.48
    ģ
    2.47
    Ĥ
    2.47
    ĥ
    2.40
    ľ
    2.40
    ĩ
    2.34
    ¤
    2.33
    Activations Density 3.089%

    No Known Activations