© 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. 25085
    Prev
    Next
    INDEX
    Explanations

    terminology related to viral genetics and endogenous processes

    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
    +0.30
    1.7%
    48
    +0.13
    0.8%
    30
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.30
    0.01
    340
    +0.13
    0.01
    148
    +0.11
    0.01
    Negative Logits
    blockList
    -1.86
    že
    -1.58
    hler
    -1.58
    ined
    -1.54
    aver
    -1.48
    sole
    -1.47
    ){
    -1.46
    oug
    -1.42
    with
    -1.41
    uler
    -1.41
    POSITIVE LOGITS
    ł
    3.96
    ¦
    3.92
    ¤
    3.87
    º
    3.87
    ķ
    3.78
    ĺ
    3.72
    Ģ
    3.67
    Ħ
    3.65
    ¾
    3.63
    ĻĤ
    3.62
    Activations Density 0.052%

    No Known Activations