© 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. 0-MLP-SM
    11. 29487
    Prev
    Next
    INDEX
    Explanations

    sorting operations in programming 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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    376
    +0.13
    0.7%
    412
    +0.10
    0.6%
    466
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    83
    +0.13
    0.01
    263
    +0.10
    0.01
    78
    +0.10
    0.01
    Negative Logits
     orgasm
    -1.66
    rely
    -1.65
    LLOW
    -1.64
     BGCOLOR
    -1.59
     ')
    -1.58
     grate
    -1.56
    printStackTrace
    -1.54
     foreground
    -1.53
     dawn
    -1.50
    "?"
    -1.49
    POSITIVE LOGITS
    »¿
    2.37
    £
    2.22
    ĩ
    2.15
    ĸ
    2.13
    ĻĤ
    2.12
    Ļª
    2.08
    İ
    2.04
    ħ
    2.03
    able
    2.03
    Ĵ
    2.02
    Activations Density 0.018%

    No Known Activations