© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 26837
    Prev
    Next
    INDEX
    Explanations

    instances of the word "coding" and references to recycling practices

    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
    283
    +0.11
    0.6%
    375
    +0.10
    0.6%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.11
    0.01
    283
    +0.10
    0.01
    451
    +0.10
    0.01
    Negative Logits
    Ļª
    -3.15
    §
    -3.08
    Ĥ
    -3.08
    ¨
    -2.95
    ĥ½
    -2.86
    IJ
    -2.73
    ¯
    -2.71
    ¾
    -2.70
    ı
    -2.68
    Ĥ¬
    -2.66
    POSITIVE LOGITS
     styles
    1.98
     style
    1.92
    idone
    1.69
     posture
    1.66
     position
    1.65
     biases
    1.64
     scene
    1.63
     modality
    1.61
     stance
    1.59
    pan
    1.56
    Activations Density 0.007%

    No Known Activations