© 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. 30494
    Prev
    Next
    INDEX
    Explanations

    references to specific months, particularly the phrase "Month 10."

    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
    287
    +0.13
    0.7%
    34
    +0.12
    0.7%
    115
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.13
    0.01
    346
    +0.12
    0.01
    287
    +0.12
    0.01
    Negative Logits
    ·
    -2.29
    ¯
    -2.23
    §
    -2.21
    ¸
    -2.13
                                           
    -2.06
    č↵        
    -2.06
                                            
    -2.06
     ↵     
    -2.06
                                       
    -2.06
    <|outofrange|>
    -2.06
    POSITIVE LOGITS
    ouin
    1.94
    lit
    1.72
    ulates
    1.71
    dream
    1.66
    ulate
    1.64
    optera
    1.63
    blind
    1.61
    lane
    1.60
    robe
    1.58
    ually
    1.56
    Activations Density 0.008%

    No Known Activations