© 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. 23245
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical measurements and properties

    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
    156
    +0.29
    1.6%
    23
    +0.15
    0.9%
    104
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    218
    +0.29
    0.04
    313
    +0.15
    0.02
    511
    +0.14
    0.03
    Negative Logits
    plots
    -1.59
     manipulations
    -1.55
    ses
    -1.50
    skins
    -1.49
     plots
    -1.44
    ipl
    -1.44
    plot
    -1.41
    ressor
    -1.41
     pleth
    -1.37
     sums
    -1.37
    POSITIVE LOGITS
     silent
    1.51
    >&
    1.45
    OID
    1.42
    rena
    1.38
    ubotu
    1.37
     FREE
    1.36
     than
    1.36
    :&
    1.33
     heart
    1.33
    NE
    1.32
    Activations Density 0.180%

    No Known Activations