© 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 EvalsExportsinterp-engineNEWAPI 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. 23662
    Prev
    Next
    INDEX
    Explanations

    numerical values or quantities

    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
    376
    +0.14
    0.8%
    403
    +0.14
    0.8%
    414
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    403
    +0.14
    0.01
    376
    +0.14
    0.01
    168
    +0.12
    0.01
    Negative Logits
    ĻĤ
    -2.35
    ĨĴ
    -2.13
    ľ
    -1.97
    Īĺ
    -1.96
    ĭ
    -1.91
    IJ
    -1.88
    Ļª
    -1.85
    į
    -1.77
    ¢
    -1.76
    Ĺ
    -1.73
    POSITIVE LOGITS
    ÃŃa
    1.89
    piece
    1.86
    ista
    1.79
    gol
    1.79
    jsfiddle
    1.75
    osse
    1.74
    oire
    1.71
    iste
    1.70
    fiddle
    1.68
    arte
    1.64
    Activations Density 0.035%

    No Known Activations