© 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 EvalsExportsAPI 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. 9728
    Prev
    Next
    INDEX
    Explanations

    references to various programming functions and structures

    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
    263
    +0.19
    1.1%
    294
    +0.14
    0.8%
    23
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    294
    +0.19
    0.08
    463
    +0.14
    0.06
    469
    +0.13
    0.09
    Negative Logits
    ľĵ
    -1.93
    ĥ
    -1.87
    ¾
    -1.70
    /-/
    -1.62
    %.
    -1.58
    Ŀ
    -1.53
     (%)
    -1.53
    Īĺ
    -1.51
    ŀ
    -1.50
    Ļª
    -1.46
    POSITIVE LOGITS
    iol
    1.50
     Salt
    1.48
     Milk
    1.45
     Son
    1.42
     Factory
    1.42
    thening
    1.39
    hua
    1.34
     injections
    1.34
     Hidden
    1.33
    uki
    1.33
    Activations Density 4.713%

    No Known Activations