© 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. 13689
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to XML schema definitions

    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
    263
    +0.18
    1.0%
    17
    +0.17
    1.0%
    354
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.18
    -0.00
    82
    +0.17
    0.05
    59
    +0.15
    0.04
    Negative Logits
     possibility
    -1.62
    ’.
    -1.62
    .’
    -1.61
    .’”
    -1.61
    ,’
    -1.60
    ].$$
    -1.53
     presence
    -1.53
     way
    -1.52
     necrosis
    -1.49
     []{
    -1.49
    POSITIVE LOGITS
    Ĥ¬
    1.49
    entary
    1.48
    ľĵ
    1.47
    mie
    1.45
    ģ
    1.45
     Pelosi
    1.44
    porter
    1.42
    utor
    1.41
    ¥
    1.38
    APTER
    1.38
    Activations Density 1.807%

    No Known Activations