© 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. 30244
    Prev
    Next
    INDEX
    Explanations

    terms related to lowering or reducing negative impacts or risks

    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
    +0.23
    1.3%
    23
    +0.14
    0.8%
    30
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.23
    0.01
    231
    +0.14
    0.01
    378
    +0.12
    0.01
    Negative Logits
    genstein
    -1.73
    teenth
    -1.69
    kowski
    -1.69
    ships
    -1.66
    erto
    -1.65
    rou
    -1.64
    neys
    -1.63
    utor
    -1.62
    ska
    -1.60
    rea
    -1.56
    POSITIVE LOGITS
    hift
    1.76
     female
    1.56
     ownership
    1.53
     death
    1.53
     life
    1.49
     suicide
    1.48
     validity
    1.45
     heaven
    1.42
     male
    1.41
     daytime
    1.41
    Activations Density 0.013%

    No Known Activations