© 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 EvalsExportsinterp-engineNEWAPI 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. 26664
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions, specifically indicating obstructive diseases

    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
    +0.15
    0.9%
    268
    +0.11
    0.6%
    148
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    268
    +0.11
    0.01
    22
    +0.11
    0.01
    Negative Logits
     full
    -1.68
    rie
    -1.55
    len
    -1.53
     total
    -1.49
     Applic
    -1.39
     greater
    -1.36
     Available
    -1.36
    ched
    -1.33
     less
    -1.32
    rian
    -1.30
    POSITIVE LOGITS
    ĻĤ
    2.91
    Ĩ
    2.70
    ¹
    2.60
    µ
    2.59
    ¡
    2.50
    Ł
    2.40
    Īĺ
    2.40
    ®
    2.29
    £
    2.27
    ´
    2.23
    Activations Density 0.016%

    No Known Activations