© 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 EvalsExportsAPI 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. 28562
    Prev
    Next
    INDEX
    Explanations

    the term "acceptable" and similar phrases indicating compliance or suitability

    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
    +0.40
    2.5%
    376
    +0.16
    1.0%
    408
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.40
    0.02
    156
    +0.16
    0.01
    347
    +0.14
    0.01
    Negative Logits
    orian
    -1.72
    roller
    -1.59
    ijo
    -1.50
    jours
    -1.48
    ĥ½
    -1.45
    FFIR
    -1.45
    srep
    -1.43
    orie
    -1.40
    iculous
    -1.38
    ÃŁ
    -1.36
    POSITIVE LOGITS
     defenses
    1.58
    amente
    1.56
     targeting
    1.54
     bases
    1.53
    ifications
    1.50
    het
    1.49
     ones
    1.49
    ently
    1.45
     targets
    1.39
    mouth
    1.38
    Activations Density 0.017%

    No Known Activations