© 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. 2-MLP-SM
    11. 22661
    Prev
    Next
    INDEX
    Explanations

    various numerical references or quantities associated with data

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    360
    +0.10
    0.6%
    3
    +0.10
    0.6%
    509
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    14
    +0.10
    0.06
    454
    +0.10
    0.01
    238
    +0.10
    0.03
    Negative Logits
     ([@
    -1.54
    imet
    -1.50
    ometers
    -1.47
    addle
    -1.44
    ages
    -1.43
     âĢķ
    -1.42
    âĨĴ
    -1.40
    ouri
    -1.40
    Kit
    -1.40
    Metric
    -1.39
    POSITIVE LOGITS
    $}
    1.64
     optimum
    1.63
     soon
    1.60
    aliana
    1.52
     \%
    1.51
     works
    1.43
    amide
    1.42
    $}}
    1.41
     percent
    1.38
    $/
    1.35
    Activations Density 0.435%

    No Known Activations