© 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. 30889
    Prev
    Next
    INDEX
    Explanations

    references to marks or markings in various contexts

    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
    376
    +0.20
    1.2%
    2
    +0.14
    0.8%
    100
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    265
    +0.20
    0.01
    499
    +0.14
    0.01
    2
    +0.13
    0.01
    Negative Logits
    §
    -1.98
    ´
    -1.86
    ı
    -1.81
    ķ
    -1.79
    Ħ
    -1.78
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.68
    Ĭ
    -1.60
    IJ
    -1.59
    Ī
    -1.59
    -1.55
    POSITIVE LOGITS
    manship
    2.92
    heet
    2.27
    creen
    1.93
    ball
    1.78
    heets
    1.72
    ional
    1.71
    balls
    1.64
    iewicz
    1.63
    aline
    1.63
    als
    1.63
    Activations Density 0.013%

    No Known Activations