© 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. 25849
    Prev
    Next
    INDEX
    Explanations

    instances of the language code "en" indicating English language references

    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
    +0.24
    1.4%
    23
    +0.13
    0.8%
    9
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    133
    +0.24
    0.04
    18
    +0.13
    0.01
    329
    +0.12
    0.02
    Negative Logits
    Ł
    -3.95
    Ľ
    -3.87
    Ŀ
    -3.82
    º
    -3.69
    ↵                             
    -3.69
    ↵                                
    -3.69
    ↵↵    
    -3.69
    ↵        
    -3.69
    č↵      
    -3.69
    <|outofrange|>
    -3.69
    POSITIVE LOGITS
    quire
    1.58
     prey
    1.54
    ittings
    1.47
     challenging
    1.45
    comings
    1.39
    pires
    1.38
    ependence
    1.37
     uncertain
    1.36
     adulthood
    1.36
     customs
    1.35
    Activations Density 0.352%

    No Known Activations