© 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. 26563
    Prev
    Next
    INDEX
    Explanations

    references to hypoxia or hypoxic conditions

    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
    156
    +0.17
    1.0%
    369
    +0.14
    0.8%
    137
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.17
    0.01
    177
    +0.14
    0.01
    137
    +0.14
    0.01
    Negative Logits
    mente
    -1.71
    fully
    -1.71
    cibly
    -1.69
    ately
    -1.66
    aterally
    -1.66
    antically
    -1.60
     else
    -1.60
    aintiff
    -1.56
     contradiction
    -1.53
    izumab
    -1.50
    POSITIVE LOGITS
    ħ
    1.98
    º
    1.81
    othet
    1.68
    ondo
    1.65
    İ
    1.62
     temperatures
    1.57
    Ľ
    1.57
    ĩ
    1.56
     (âī¥
    1.52
    ·
    1.50
    Activations Density 0.041%

    No Known Activations