© 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. 25149
    Prev
    Next
    INDEX
    Explanations

    references to website structures or links

    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
    329
    +0.14
    0.8%
    358
    +0.13
    0.7%
    48
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2
    +0.14
    0.12
    412
    +0.13
    0.14
    282
    +0.13
    0.13
    Negative Logits
    ¿½
    -5.17
    ¬
    -5.09
    ħ
    -4.95
    ®
    -4.91
    ¾
    -4.88
    ¸
    -4.77
    ļ
    -4.76
    ĨĴ
    -4.75
    IJ
    -4.74
    «
    -4.71
    POSITIVE LOGITS
     emergency
    1.63
    rog
    1.56
    operative
    1.55
    ät
    1.50
    avern
    1.49
    brace
    1.47
    TP
    1.45
    act
    1.43
    mouth
    1.42
     chance
    1.41
    Activations Density 2.984%

    No Known Activations