© 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. 22758
    Prev
    Next
    INDEX
    Explanations

    elements of code or programming constructs

    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
    +0.15
    0.8%
    25
    +0.14
    0.8%
    412
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.15
    0.04
    30
    +0.14
    0.04
    56
    +0.12
    0.07
    Negative Logits
    Simplify
    -1.70
    č↵č↵
    -1.58
    les
    -1.58
    Definitions
    -1.50
    ="'$(
    -1.49
     Authors
    -1.42
    IEEE
    -1.38
     regard
    -1.38
     Writ
    -1.34
    ITION
    -1.33
    POSITIVE LOGITS
    ¶
    2.71
    ģ
    2.22
    ĩ
    2.21
    ij
    2.14
    £
    2.00
    Ģ
    1.96
    Ŀ
    1.96
    ł
    1.95
    ļ
    1.95
    Ļ
    1.94
    Activations Density 0.572%

    No Known Activations