© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26789
    Prev
    Next
    INDEX
    Explanations

    conditional statements and boolean return types

    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
    98
    +0.14
    0.8%
    33
    +0.13
    0.7%
    131
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.14
    0.04
    40
    +0.13
    0.02
    92
    +0.13
    0.01
    Negative Logits
    ³
    -3.04
    Īĺ
    -2.94
    §
    -2.92
    ¾
    -2.91
    ±
    -2.91
    ¹
    -2.72
    Ŀ
    -2.66
    ª
    -2.66
    Į
    -2.62
    ®
    -2.53
    POSITIVE LOGITS
    aked
    1.62
    junction
    1.61
    olk
    1.52
    taient
    1.49
    "?>
    1.44
     “[
    1.44
    afx
    1.43
    ”
    1.43
    liner
    1.42
    appa
    1.42
    Activations Density 0.363%

    No Known Activations