© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 30509
    Prev
    Next
    INDEX
    Explanations

    the concept of flying or flight-related terms

    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
    +0.14
    0.8%
    305
    +0.13
    0.7%
    52
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    305
    +0.14
    0.02
    52
    +0.13
    0.02
    429
    +0.13
    0.02
    Negative Logits
    plasia
    -1.97
     brow
    -1.72
    isex
    -1.51
    illance
    -1.50
     beauty
    -1.49
     sake
    -1.48
    keleton
    -1.44
    undry
    -1.44
    herin
    -1.43
    iser
    -1.42
    POSITIVE LOGITS
    ¾
    3.78
    ģ
    3.75
    ´
    3.60
                                             
    3.55
    ↵                                                       
    3.55
    ↵↵↵       
    3.55
     ↵  
    3.55
    <|outofrange|>
    3.55
    ↵↵             
    3.55
    ↵↵                                
    3.55
    Activations Density 0.016%

    No Known Activations