© 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. 31265
    Prev
    Next
    INDEX
    Explanations

    instances of the word "MY" as well as its relevance and 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
    156
    +0.12
    0.6%
    230
    +0.11
    0.6%
    394
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.12
    0.01
    230
    +0.11
    0.01
    88
    +0.11
    0.01
    Negative Logits
    icity
    -1.77
     ours
    -1.76
     mine
    -1.59
    ity
    -1.58
    ifying
    -1.53
     GMT
    -1.50
    ights
    -1.49
     blocked
    -1.47
    ucle
    -1.46
     exchanged
    -1.45
    POSITIVE LOGITS
    ª
    2.05
    croft
    1.82
    ģ
    1.78
    anmar
    1.71
    Ĥ
    1.68
    stown
    1.64
    walks
    1.60
    Ķ
    1.55
    İ
    1.53
    olo
    1.50
    Activations Density 0.036%

    No Known Activations