© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25295
    Prev
    Next
    INDEX
    Explanations

    the word "born" and variations of it, indicating references to birth or early origins

    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
    433
    +0.17
    1.0%
    465
    +0.13
    0.7%
    23
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    433
    +0.17
    0.02
    158
    +0.13
    0.02
    122
    +0.13
    0.01
    Negative Logits
    ·¸
    -3.98
      ↵
    -3.92
    <|outofrange|>
    -3.92
     ↵
    -3.92
    ↵
    -3.92
    ↵↵
    -3.92
             ↵
    -3.92
    -3.92
    ↵Č
    -3.92
    <|outofrange|>
    -3.92
    POSITIVE LOGITS
    )\]
    1.60
    amping
    1.58
    MENTS
    1.46
    inkling
    1.40
    hift
    1.36
    )\].
    1.35
    essential
    1.34
     obtained
    1.34
     concluded
    1.34
     Born
    1.34
    Activations Density 0.122%

    No Known Activations