© 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. 23729
    Prev
    Next
    INDEX
    Explanations

    terms related to safety, health, and productivity 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/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
    310
    +0.14
    0.8%
    190
    +0.12
    0.7%
    282
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.14
    0.11
    120
    +0.12
    0.12
    287
    +0.11
    0.13
    Negative Logits
     oneself
    -1.73
    ¿½
    -1.69
     etc
    -1.65
    ķ
    -1.57
                  ↵
    -1.56
    ↵
    -1.56
    <|outofrange|>
    -1.56
    čč
    -1.56
    <|outofrange|>
    -1.56
    ↵
    -1.56
    POSITIVE LOGITS
    liament
    1.76
    ylum
    1.54
    '>
    1.46
    capt
    1.45
    oden
    1.42
    highlight
    1.40
    bracket
    1.37
    breviations
    1.35
    matched
    1.34
    raham
    1.32
    Activations Density 2.039%

    No Known Activations