© 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. 24477
    Prev
    Next
    INDEX
    Explanations

    references to the PHP programming language and its versions, particularly in the context of code examples and principles

    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
    +0.20
    1.1%
    23
    +0.14
    0.8%
    9
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.20
    0.02
    23
    +0.14
    0.01
    311
    +0.14
    0.02
    Negative Logits
    inux
    -1.79
    uscript
    -1.60
     Fiction
    -1.56
    izumab
    -1.53
    ~/
    -1.52
    icillin
    -1.51
    cco
    -1.50
    craft
    -1.47
     virtues
    -1.42
     Writers
    -1.42
    POSITIVE LOGITS
    ¢
    2.64
    ł
    2.48
    ¨
    2.25
    ĺ
    2.23
    ¸
    2.17
    ·
    2.12
    ¦
    2.09
    ³
    2.08
    ij
    2.07
    ²
    2.02
    Activations Density 0.093%

    No Known Activations