© 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. 30587
    Prev
    Next
    INDEX
    Explanations

    information about legal proceedings and court rulings

    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
    478
    +0.15
    0.8%
    400
    +0.13
    0.7%
    369
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.15
    0.02
    350
    +0.13
    0.02
    400
    +0.13
    0.01
    Negative Logits
    heit
    -1.62
    ા
    -1.56
    zes
    -1.53
    ayout
    -1.52
    ther
    -1.46
    ız
    -1.45
     dehydrogenase
    -1.44
    izard
    -1.42
    icht
    -1.40
    à«
    -1.39
    POSITIVE LOGITS
    ½
    1.94
     numerous
    1.65
    ĺ
    1.57
    ¼
    1.56
    Ń
    1.51
    Ĺ
    1.47
    IJ
    1.44
    noreply
    1.44
    ¸
    1.42
    ²
    1.42
    Activations Density 0.073%

    No Known Activations