© 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. 24264
    Prev
    Next
    INDEX
    Explanations

    instances of code or command structure within programming or configuration documents

    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
    207
    +0.16
    0.9%
    371
    +0.14
    0.8%
    454
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    207
    +0.16
    0.05
    59
    +0.14
    0.01
    376
    +0.13
    0.04
    Negative Logits
    alities
    -1.49
    ^](#
    -1.45
     Appendix
    -1.44
    atorium
    -1.43
    abulary
    -1.40
    agogue
    -1.39
     limitations
    -1.38
    arrant
    -1.38
    abin
    -1.32
    aval
    -1.31
    POSITIVE LOGITS
    Ī
    3.09
    «
    3.07
    ī
    2.91
    ¡
    2.87
    ĭ
    2.82
    Ŀ
    2.81
    ²
    2.77
    Ń
    2.75
    ŀ
    2.74
    ·
    2.70
    Activations Density 0.606%

    No Known Activations