© 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. 29114
    Prev
    Next
    INDEX
    Explanations

    the word "coupled."

    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
    +0.19
    1.1%
    148
    +0.13
    0.7%
    445
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.19
    0.01
    346
    +0.13
    0.01
    24
    +0.11
    0.01
    Negative Logits
    ĨĴ
    -1.88
    ĥ½
    -1.74
    ¯
    -1.74
    orer
    -1.69
    ĩ
    -1.68
    Ģ
    -1.61
    ľĵ
    -1.60
    umab
    -1.58
    ellow
    -1.57
    ors
    -1.56
    POSITIVE LOGITS
     thereto
    1.78
     quarters
    1.55
     encounters
    1.52
     with
    1.51
     meals
    1.50
    town
    1.48
     sentences
    1.47
     adolescence
    1.45
    mans
    1.44
     alia
    1.44
    Activations Density 0.016%

    No Known Activations