© 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. 31008
    Prev
    Next
    INDEX
    Explanations

    references to legal case details and court proceedings

    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
    374
    +0.13
    0.7%
    410
    +0.13
    0.7%
    393
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.13
    0.02
    21
    +0.13
    0.02
    410
    +0.13
    0.03
    Negative Logits
    gener
    -1.72
    (){
    -1.68
    irt
    -1.63
    "}](#
    -1.61
    tes
    -1.60
    bserver
    -1.59
    !”
    -1.57
    ?”
    -1.54
    ”.
    -1.53
    ird
    -1.53
    POSITIVE LOGITS
    č↵
    2.55
    č↵č↵
    2.55
    ↵
    2.55
     ↵
    2.55
    ↵
    2.55
    ↵
    2.55
    ↵
    2.55
    2.55
    č↵
    2.55
    2.55
    Activations Density 0.092%

    No Known Activations