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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28285
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and constructs

    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
    23
    +0.20
    1.2%
    53
    +0.18
    1.0%
    247
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    133
    +0.20
    0.13
    53
    +0.18
    0.11
    247
    +0.15
    0.10
    Negative Logits
    ural
    -1.63
    base
    -1.57
     sciences
    -1.56
    fast
    -1.50
    ].[
    -1.46
    wright
    -1.43
    riz
    -1.43
    atÄĥ
    -1.41
    ically
    -1.40
    ics
    -1.40
    POSITIVE LOGITS
     finally
    1.65
    sun
    1.54
    being
    1.46
    ĵ
    1.45
    rees
    1.42
        
    1.39
    	
    1.36
    ..."
    1.35
    oves
    1.33
    ãĢĢ
    1.31
    Activations Density 0.134%

    No Known Activations