© 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. Residuals
    9. 4-RES-SM
    11. 11748
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and sorting sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/4-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.20
    1.2%
    21
    +0.12
    0.7%
    279
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    177
    +0.20
    0.04
    279
    +0.12
    0.04
    275
    +0.10
    0.01
    Negative Logits
    liest
    -1.85
    achine
    -1.55
    atics
    -1.52
    aments
    -1.51
    ying
    -1.44
    vas
    -1.42
     \'
    -1.42
    oria
    -1.38
    ament
    -1.37
    \'
    -1.36
    POSITIVE LOGITS
    Ĺ
    1.97
    ĩ
    1.94
    ļ
    1.86
    ¬
    1.85
    IJ
    1.84
    ı
    1.81
    ī
    1.77
    Ķ
    1.76
    Ŀ
    1.76
    į
    1.76
    Activations Density 0.123%

    No Known Activations