© 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. 25301
    Prev
    Next
    INDEX
    Explanations

    repeated punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    398
    +0.13
    0.7%
    14
    +0.12
    0.6%
    62
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.13
    0.36
    23
    +0.12
    0.31
    494
    +0.11
    0.25
    Negative Logits
    µ
    -2.68
    ³
    -2.62
    Ĭ
    -2.54
    Ĩ
    -2.54
    ½
    -2.51
    °
    -2.40
    ´
    -2.40
    ĸ
    -2.39
    º
    -2.36
    ļ
    -2.35
    POSITIVE LOGITS
     shr
    1.80
    ester
    1.66
    yrus
    1.62
    amus
    1.55
    à°¿
    1.54
    edi
    1.53
    anian
    1.52
     funnel
    1.49
    pace
    1.48
    anza
    1.45
    Activations Density 3.060%

    No Known Activations