© 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. 1-RES-SM
    11. 28947
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and structures involving cells and their interactions

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.16
    0.9%
    148
    +0.15
    0.9%
    71
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.16
    0.01
    308
    +0.15
    0.01
    315
    +0.13
    0.01
    Negative Logits
    že
    -1.69
    unnumbered
    -1.64
     euthan
    -1.61
    chers
    -1.61
    ouses
    -1.56
     fatal
    -1.55
    unting
    -1.49
    woke
    -1.48
    wers
    -1.46
     suicidal
    -1.46
    POSITIVE LOGITS
    £
    2.81
    Ģ
    2.74
    Ł
    2.71
    ŀ
    2.70
    ¿½
    2.67
    ķ
    2.65
    ĻĤ
    2.62
    »¿
    2.54
    ł
    2.53
    ĺ
    2.50
    Activations Density 0.025%

    No Known Activations