© 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. 24873
    Prev
    Next
    INDEX
    Explanations

    references to programming languages or coding contexts

    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
    156
    +0.17
    1.0%
    326
    +0.12
    0.7%
    426
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.17
    0.06
    326
    +0.12
    0.02
    23
    +0.12
    0.02
    Negative Logits
     Defense
    -1.66
    ureus
    -1.63
    jsfiddle
    -1.51
    anguage
    -1.51
     anonym
    -1.48
    =-
    -1.47
    ppler
    -1.43
    indi
    -1.40
     offic
    -1.40
     google
    -1.39
    POSITIVE LOGITS
    ľ
    1.64
    elike
    1.54
    ailing
    1.47
    akes
    1.43
    ij
    1.40
    edly
    1.39
    heated
    1.35
    tails
    1.34
    t
    1.34
    weight
    1.34
    Activations Density 0.679%

    No Known Activations