© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 24964
    Prev
    Next
    INDEX
    Explanations

    instances of case or citation numbers in legal documents

    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
    23
    +0.18
    1.0%
    156
    +0.17
    0.9%
    458
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    213
    +0.18
    0.03
    317
    +0.17
    0.02
    59
    +0.14
    0.00
    Negative Logits
    "}](#
    -1.63
    stit
    -1.60
    clinical
    -1.48
    iaz
    -1.48
    bench
    -1.44
    eLife
    -1.43
    journal
    -1.42
    blank
    -1.42
    matics
    -1.41
    shell
    -1.41
    POSITIVE LOGITS
    keit
    2.29
     slack
    1.69
     something
    1.66
    irs
    1.64
     distance
    1.56
    illes
    1.56
     nowhere
    1.47
    lez
    1.45
    iced
    1.41
    []{
    1.38
    Activations Density 0.164%

    No Known Activations