© 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. Residuals
    9. 4-RES-SM
    11. 10676
    Prev
    Next
    INDEX
    Explanations

    file and directory management commands or related terms

    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
    252
    +0.15
    0.8%
    31
    +0.14
    0.8%
    251
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.15
    0.06
    252
    +0.14
    0.04
    423
    +0.13
    0.06
    Negative Logits
    ĥ½
    -3.23
    º
    -3.11
    §
    -2.85
    Ļ
    -2.85
    »
    -2.77
    Ī
    -2.75
    ħ
    -2.75
    į
    -2.75
    ·¸
    -2.72
    ª
    -2.70
    POSITIVE LOGITS
     files
    4.36
     file
    4.26
     File
    3.91
     Files
    3.84
    file
    3.81
    File
    3.77
     folder
    3.76
     directories
    3.62
    Files
    3.62
     filename
    3.59
    Activations Density 1.307%

    No Known Activations