© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 25484
    Prev
    Next
    INDEX
    Explanations

    programming constructs and data structure attributes

    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
    23
    +0.23
    1.3%
    326
    +0.11
    0.6%
    12
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.23
    0.07
    232
    +0.11
    0.09
    491
    +0.10
    0.06
    Negative Logits
     instance
    -1.84
     Jobs
    -1.78
    poser
    -1.67
     hasht
    -1.58
    googleapis
    -1.57
     ingredient
    -1.56
    pace
    -1.53
    ="'$(
    -1.49
     etc
    -1.48
     example
    -1.48
    POSITIVE LOGITS
    °
    3.04
    ľ
    3.03
    ĩ
    2.97
    ´
    2.94
    ¡
    2.90
    ·
    2.88
    Ĺ
    2.87
    µ
    2.86
    ķ
    2.85
    Ļ
    2.83
    Activations Density 1.096%

    No Known Activations