© 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. 27829
    Prev
    Next
    INDEX
    Explanations

    instances of code or programming-related keywords

    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
    471
    +0.13
    0.8%
    376
    +0.13
    0.8%
    241
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.13
    0.02
    397
    +0.13
    0.02
    241
    +0.12
    0.02
    Negative Logits
    ·¸
    -4.29
    ĭ
    -4.12
    »¿
    -3.99
    ¿½
    -3.92
    ĸ´
    -3.60
    ±
    -3.57
    ´
    -3.42
    İ
    -3.42
    Īĺ
    -3.41
    ĨĴ
    -3.33
    POSITIVE LOGITS
    mos
    1.77
    vre
    1.64
    ios
    1.58
    gary
    1.55
    enstein
    1.54
    inet
    1.47
    DNA
    1.47
     pockets
    1.45
    endar
    1.43
     margins
    1.43
    Activations Density 0.011%

    No Known Activations