© 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. 23893
    Prev
    Next
    INDEX
    Explanations

    references to PHP code or syntax

    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
    489
    +0.14
    0.8%
    465
    +0.12
    0.7%
    339
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.14
    0.02
    489
    +0.12
    0.01
    275
    +0.12
    0.00
    Negative Logits
    ¬
    -1.85
    eren
    -1.80
    oche
    -1.70
    "</
    -1.63
    ¥
    -1.62
    ¿½
    -1.58
    «
    -1.57
    Ŀ
    -1.54
    ľ
    -1.50
    ĻĤ
    -1.50
    POSITIVE LOGITS
    ctors
    1.54
    ellation
    1.49
    offs
    1.48
    wagen
    1.45
    engers
    1.43
    balls
    1.41
     EVs
    1.40
    nel
    1.40
    icle
    1.37
    icz
    1.36
    Activations Density 0.092%

    No Known Activations