© 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. 24337
    Prev
    Next
    INDEX
    Explanations

    references to legal or procedural terminology

    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
    111
    +0.57
    4.2%
    156
    +0.41
    3.0%
    258
    +0.10
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    221
    +0.57
    0.02
    174
    +0.41
    0.03
    200
    +0.10
    0.03
    Negative Logits
    ħ
    -5.06
    ľĵ
    -5.01
    ĥ
    -5.01
    Ł
    -5.00
    Ľ
    -4.99
    ®
    -4.97
    ĻĤ
    -4.93
    ģ
    -4.90
    ¨
    -4.88
    £
    -4.88
    POSITIVE LOGITS
     underlying
    1.67
    witz
    1.60
     contributors
    1.48
     accelerator
    1.34
     presentations
    1.33
     constituents
    1.33
     independence
    1.28
    ères
    1.27
    *]{}.
    1.27
     products
    1.26
    Activations Density 0.049%

    No Known Activations