© 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. 12990
    Prev
    Next
    INDEX
    Explanations

    terms related to acute medical 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
    +0.31
    1.8%
    443
    +0.12
    0.7%
    186
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.31
    0.00
    443
    +0.12
    0.01
    18
    +0.11
    0.01
    Negative Logits
     sizeof
    -1.62
    ÑĢÑĥг
    -1.61
    chitz
    -1.59
    Ñĥп
    -1.58
    otec
    -1.56
    sizeof
    -1.52
    аÑģÑĤ
    -1.52
    аÑģÑģ
    -1.49
    located
    -1.49
    že
    -1.45
    POSITIVE LOGITS
    £
    3.25
    ł
    3.16
    Ł
    3.09
    º
    2.92
    ļ
    2.92
    ĥ
    2.86
    ¢
    2.79
    Ŀ
    2.56
    ī
    2.35
    ³
    2.34
    Activations Density 0.036%

    No Known Activations