© 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. 4-RES-SM
    11. 14389
    Prev
    Next
    INDEX
    Explanations

    legal references and case law citations

    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
    21
    +0.15
    0.9%
    216
    +0.12
    0.7%
    255
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    216
    +0.15
    0.05
    57
    +0.12
    0.04
    477
    +0.11
    0.04
    Negative Logits
     displayed
    -1.40
    itian
    -1.40
    tic
    -1.34
     landscape
    -1.33
    mered
    -1.33
     replicated
    -1.31
     equation
    -1.31
    ches
    -1.30
     simulated
    -1.29
    roup
    -1.27
    POSITIVE LOGITS
    ·
    2.46
    ŀ
    2.45
    ij
    2.43
    ¿½
    2.42
    ¢
    2.22
    ĥ½
    2.21
    ²
    2.15
    Ŀ
    2.12
    Ļª
    2.08
     Wn
    2.07
    Activations Density 0.196%

    No Known Activations