© 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. 23634
    Prev
    Next
    INDEX
    Explanations

    references to governmental and organizational entities, particularly related to the United States

    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
    145
    +0.13
    0.7%
    80
    +0.12
    0.7%
    66
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.13
    0.07
    386
    +0.12
    0.03
    80
    +0.11
    0.06
    Negative Logits
     my
    -1.52
     nucleus
    -1.50
    chell
    -1.49
    cher
    -1.45
    MAP
    -1.41
     alive
    -1.37
    mur
    -1.36
    pt
    -1.35
    rob
    -1.33
    uin
    -1.32
    POSITIVE LOGITS
    neck
    1.71
    bies
    1.68
    bie
    1.58
    ftware
    1.55
     Dress
    1.47
    APTER
    1.45
     Bd
    1.42
    cloth
    1.41
    enburg
    1.39
     Fla
    1.39
    Activations Density 0.526%

    No Known Activations