© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 25712
    Prev
    Next
    INDEX
    Explanations

    words related to security and safety

    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
    376
    +0.15
    0.8%
    156
    +0.12
    0.7%
    254
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.15
    0.02
    251
    +0.12
    0.02
    359
    +0.11
    0.02
    Negative Logits
    awk
    -1.70
    rox
    -1.43
    asma
    -1.42
    asc
    -1.41
    да
    -1.34
    AFFIRMED
    -1.31
    sed
    -1.30
    CO
    -1.29
    Affirmed
    -1.29
    rog
    -1.29
    POSITIVE LOGITS
    amente
    1.96
    iously
    1.79
    edly
    1.70
    ties
    1.69
    imento
    1.61
    iu
    1.59
    ingly
    1.59
    guards
    1.56
    gered
    1.56
    gery
    1.50
    Activations Density 0.013%

    No Known Activations