© 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. 23385
    Prev
    Next
    INDEX
    Explanations

    topics related to child custody and legal proceedings

    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
    +0.20
    1.1%
    176
    +0.13
    0.8%
    23
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.20
    0.13
    430
    +0.13
    0.07
    170
    +0.13
    0.08
    Negative Logits
    "}](#
    -1.90
     RFC
    -1.59
    pora
    -1.51
    bourg
    -1.47
    80211
    -1.47
    pcbi
    -1.45
     (@
    -1.42
     persona
    -1.41
    framework
    -1.40
    wald
    -1.38
    POSITIVE LOGITS
    ĻĤ
    1.71
     cleansing
    1.71
    ))$
    1.63
    breviations
    1.63
    ently
    1.62
    ogether
    1.62
    ()));
    1.52
    ))$.
    1.50
     yours
    1.42
     alright
    1.40
    Activations Density 5.683%

    No Known Activations