© 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. 28648
    Prev
    Next
    INDEX
    Explanations

    the term “prime” related to prime numbers or prime attributes

    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
    141
    +0.15
    0.8%
    72
    +0.13
    0.7%
    406
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    389
    +0.15
    0.01
    94
    +0.13
    0.01
    3
    +0.12
    0.01
    Negative Logits
    ľĵ
    -1.78
    Īĺ
    -1.75
     ";
    -1.65
    rVert
    -1.64
    ¿
    -1.63
    .");
    -1.63
     '</
    -1.59
     */
    -1.57
    ytes
    -1.56
    Ĥ¬
    -1.55
    POSITIVE LOGITS
    writers
    1.84
    casters
    1.74
    yards
    1.67
    ños
    1.66
     fans
    1.61
    arily
    1.61
    vir
    1.59
    erals
    1.52
    cribed
    1.52
     means
    1.52
    Activations Density 0.036%

    No Known Activations