© 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 EvalsExportsAPI 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. 24590
    Prev
    Next
    INDEX
    Explanations

    references 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
    156
    +0.43
    2.6%
    353
    +0.11
    0.6%
    293
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.43
    0.04
    353
    +0.11
    0.03
    30
    +0.10
    0.03
    Negative Logits
    éri
    -1.54
    ÃŃs
    -1.53
    ymphony
    -1.45
    aintiff
    -1.44
    levard
    -1.44
    :`
    -1.43
    atorium
    -1.36
    clud
    -1.34
    anza
    -1.32
    ág
    -1.29
    POSITIVE LOGITS
     hell
    1.51
    ously
    1.42
    İ
    1.39
     py
    1.32
    cribing
    1.31
     squir
    1.31
     aside
    1.30
     Dana
    1.29
     mixtures
    1.26
     huh
    1.25
    Activations Density 0.095%

    No Known Activations