© 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. Residuals
    9. 2-RES-SM
    11. 9635
    Prev
    Next
    INDEX
    Explanations

    mentions of specific years or timeframes

    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/2-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.2.hook_resid_post
    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
    358
    +0.13
    0.7%
    50
    +0.12
    0.7%
    350
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    364
    +0.13
    0.04
    163
    +0.12
    0.03
    297
    +0.11
    0.04
    Negative Logits
     ↵
    -2.66
    ↵↵
    -2.66
           ↵
    -2.66
    ↵
    -2.66
    -2.66
         ↵
    -2.66
    č↵
    -2.66
    -2.66
    -2.66
    ↵
    -2.66
    POSITIVE LOGITS
    nel
    2.50
    ning
    2.41
    book
    2.38
    nings
    2.27
    ned
    2.11
    ality
    1.94
    lights
    1.92
    forth
    1.83
    nen
    1.77
    gio
    1.75
    Activations Density 0.193%

    No Known Activations