© 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. 1-RES-SM
    11. 25604
    Prev
    Next
    INDEX
    Explanations

    class inheritance and implementation in code structures

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    290
    +0.15
    0.9%
    376
    +0.15
    0.9%
    478
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    290
    +0.15
    0.02
    231
    +0.15
    0.02
    317
    +0.15
    0.02
    Negative Logits
    acker
    -1.64
     served
    -1.64
    andel
    -1.63
    lights
    -1.58
     won
    -1.51
    oot
    -1.51
    aster
    -1.50
    stick
    -1.45
    lew
    -1.44
    etus
    -1.44
    POSITIVE LOGITS
    ¿
    2.29
    £
    2.25
    ĭ
    2.20
    µ
    2.19
    Ļª
    2.16
    áĢ¯
    2.02
    ³
    1.95
    ĨĴ
    1.94
    ı
    1.92
    ĻĤ
    1.90
    Activations Density 0.077%

    No Known Activations