© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26641
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "to undermine."

    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
    369
    +0.17
    1.0%
    63
    +0.12
    0.7%
    419
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.17
    0.05
    63
    +0.12
    0.06
    225
    +0.11
    0.07
    Negative Logits
    ches
    -1.68
     neut
    -1.64
    atively
    -1.59
     away
    -1.57
    ights
    -1.54
    ch
    -1.54
    utations
    -1.53
    itely
    -1.50
    acular
    -1.50
     down
    -1.50
    POSITIVE LOGITS
      ↵ 
    2.21
    ↵             
    2.21
     ↵     
    2.21
    ↵↵↵       
    2.21
    č↵               
    2.21
    <|outofrange|>
    2.21
    ↵↵                                         
    2.21
             
    2.21
    ↵  âĢĥ
    2.21
                    
    2.21
    Activations Density 0.670%

    No Known Activations