© 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. 26043
    Prev
    Next
    INDEX
    Explanations

    terms related to regulation and the regulatory processes in various contexts

    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
    156
    +0.28
    1.7%
    376
    +0.24
    1.5%
    148
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    484
    +0.28
    0.01
    156
    +0.24
    0.01
    498
    +0.15
    0.01
    Negative Logits
     reviewed
    -1.47
    ksen
    -1.43
    brahim
    -1.43
    lli
    -1.39
    illard
    -1.37
    llo
    -1.36
    Berry
    -1.35
    stanbul
    -1.34
    cies
    -1.33
     Publ
    -1.33
    POSITIVE LOGITS
    ĻĤ
    1.73
     resistance
    1.51
     them
    1.47
    ¿½
    1.41
    ulating
    1.39
     limits
    1.39
    ¥
    1.36
    ément
    1.35
    ligt
    1.35
     boundaries
    1.34
    Activations Density 0.160%

    No Known Activations