© 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. 2-MLP-SM
    11. 23007
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and their treatments

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    156
    +0.36
    2.2%
    23
    +0.17
    1.1%
    367
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    367
    +0.36
    0.03
    511
    +0.17
    0.04
    232
    +0.12
    0.06
    Negative Logits
    ĥ½
    -2.70
    ·¸
    -2.59
    ↵
    -2.59
    ↵
    -2.59
    <|outofrange|>
    -2.59
    č↵
    -2.59
     ↵
    -2.59
    -2.59
              ↵
    -2.59
    ↵
    -2.58
    POSITIVE LOGITS
     (_
    1.47
     erect
    1.45
     echo
    1.44
     supp
    1.41
     alive
    1.39
     thread
    1.39
     "$(
    1.39
     glue
    1.38
     mess
    1.37
     tid
    1.37
    Activations Density 0.387%

    No Known Activations