© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 26306
    Prev
    Next
    INDEX
    Explanations

    biological and viral terminology

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    271
    +0.19
    1.1%
    326
    +0.17
    1.0%
    202
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    221
    +0.19
    0.06
    271
    +0.17
    0.00
    164
    +0.13
    0.07
    Negative Logits
    Funding
    -1.88
     ourselves
    -1.83
    Solve
    -1.67
    č↵č↵
    -1.58
    GET
    -1.58
    ESH
    -1.57
    ORM
    -1.56
    ADDR
    -1.52
     yourself
    -1.48
     momentum
    -1.46
    POSITIVE LOGITS
    ¸
    4.05
    ·
    4.01
    ľ
    3.79
    Ń
    3.76
    ī
    3.75
    «
    3.74
    ¼
    3.67
    ³
    3.55
    ĻĤ
    3.54
    Ĺ
    3.51
    Activations Density 0.681%

    No Known Activations