© 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. 24014
    Prev
    Next
    INDEX
    Explanations

    references to web-related content and technologies

    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
    +0.31
    1.8%
    359
    +0.10
    0.6%
    23
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    491
    +0.31
    0.02
    417
    +0.10
    0.03
    218
    +0.10
    0.02
    Negative Logits
    inib
    -1.71
    udad
    -1.49
    imod
    -1.49
    ActivityThread
    -1.45
     herself
    -1.45
    izumab
    -1.44
    ylase
    -1.43
    ieu
    -1.43
    ovy
    -1.42
    )...
    -1.40
    POSITIVE LOGITS
     extremes
    1.62
     define
    1.61
     divided
    1.55
    ration
    1.42
     evenly
    1.39
    ricting
    1.38
    ging
    1.37
     LLP
    1.35
     outside
    1.33
    aging
    1.33
    Activations Density 0.150%

    No Known Activations