Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27016
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental issues and climate change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    +0.14
    0.8%
    186
    +0.10
    0.6%
    199
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.14
    0.03
    156
    +0.10
    0.13
    199
    +0.10
    0.10
    Negative Logits
    ĥ½
    -2.23
    ¿
    -1.94
    »
    -1.91
    ·
    -1.91
    ·¸
    -1.85
    ↵                                                                
    -1.84
              ↵ 
    -1.84
    č↵        
    -1.84
    ↵                
    -1.84
    ↵↵                   
    -1.84
    POSITIVE LOGITS
     causes
    1.82
    naire
    1.79
     etc
    1.76
    ?,
    1.65
     (§
    1.63
    holder
    1.61
     [...]
    1.59
    arium
    1.59
    ?",
    1.58
     occasions
    1.55
    Activations Density 1.710%

    No Known Activations