© 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 EvalsExportsinterp-engineNEWAPI 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. 23462
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific measurements and calculations

    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
    317
    +0.12
    0.7%
    25
    +0.11
    0.6%
    478
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.12
    0.12
    100
    +0.11
    0.11
    23
    +0.10
    0.04
    Negative Logits
    ings
    -1.92
    liness
    -1.78
    iors
    -1.63
    resses
    -1.62
    field
    -1.61
    iels
    -1.55
    ements
    -1.53
    ¢
    -1.51
    ¥
    -1.51
    lies
    -1.49
    POSITIVE LOGITS
     trust
    1.54
     Boulevard
    1.52
     sob
    1.43
    ene
    1.38
     anesthetized
    1.27
    think
    1.27
     pept
    1.26
    wegian
    1.23
    bid
    1.22
    erd
    1.21
    Activations Density 1.663%

    No Known Activations