© 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. 29004
    Prev
    Next
    INDEX
    Explanations

    mentions of substances related to pain relief or medications

    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
    111
    +0.16
    0.9%
    397
    +0.12
    0.7%
    161
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.01
    161
    +0.12
    0.01
    300
    +0.12
    0.01
    Negative Logits
    Ĥ¬
    -2.00
    Į
    -1.98
    Ī
    -1.95
    ĸ´
    -1.87
    ´
    -1.80
    ¿
    -1.78
    ¬
    -1.72
    ª
    -1.70
    Īĺ
    -1.70
    Ĺ
    -1.66
    POSITIVE LOGITS
    esan
    1.75
    ceedings
    1.67
    bugs
    1.66
    bank
    1.66
    aho
    1.65
    ique
    1.64
    ://
    1.64
    ifically
    1.63
    :`
    1.59
    ics
    1.57
    Activations Density 0.006%

    No Known Activations