© 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. 23807
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical and health conditions

    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
    2.1%
    480
    +0.11
    0.7%
    262
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.36
    0.10
    303
    +0.11
    0.08
    472
    +0.10
    0.09
    Negative Logits
    ĸ
    -3.48
    ¤
    -3.45
      ↵
    -3.34
    -3.34
    <|outofrange|>
    -3.34
    ↵
    -3.34
    ↵↵↵
    -3.34
     ↵
    -3.34
    ↵
    -3.34
    -3.34
    POSITIVE LOGITS
    )',
    1.73
    )**
    1.61
    itations
    1.46
    tering
    1.44
    ilar
    1.44
    itative
    1.39
    .**]{}
    1.38
    amics
    1.34
    ulations
    1.33
    hibition
    1.33
    Activations Density 2.876%

    No Known Activations