© 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. 0-MLP-SM
    11. 26225
    Prev
    Next
    INDEX
    Explanations

    repetitions or mentions of "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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    180
    +0.14
    0.8%
    247
    +0.12
    0.7%
    100
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    180
    +0.14
    0.04
    0
    +0.12
    0.03
    14
    +0.12
    0.03
    Negative Logits
    ¶
    -2.52
    ij
    -2.40
    ĥ½
    -2.25
    ³
    -2.23
    ±
    -2.16
    ¸
    -2.04
    ·
    -1.99
    ĻĤ
    -1.95
     ↵
    -1.89
    -1.89
    POSITIVE LOGITS
    cript
    2.07
    oft
    1.89
    manship
    1.85
    heet
    1.80
    works
    1.78
    man
    1.66
    pun
    1.62
    dale
    1.60
    ément
    1.60
     tends
    1.53
    Activations Density 0.544%

    No Known Activations