© 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. 14257
    Prev
    Next
    INDEX
    Explanations

    specific names or entities related to legal cases or 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/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
    24
    +0.12
    0.7%
    254
    +0.11
    0.6%
    417
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.12
    0.01
    475
    +0.11
    0.03
    302
    +0.11
    0.04
    Negative Logits
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    -1.94
    ±
    -1.94
    ī
    -1.92
    ĭ
    -1.91
    ²
    -1.90
    Ń
    -1.89
    °
    -1.88
    ©
    -1.82
    ¹
    -1.81
    Īĺ
    -1.80
    POSITIVE LOGITS
     AM
    3.75
     Am
    3.72
    am
    3.57
    AM
    3.49
    Am
    3.22
    ams
    2.68
     am
    2.64
    amate
    2.50
    amis
    2.47
    amic
    2.46
    Activations Density 0.516%

    No Known Activations