© 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. 10411
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "entirety" or "wholeness."

    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
    362
    +0.13
    0.7%
    241
    +0.12
    0.7%
    456
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.03
    170
    +0.12
    0.02
    456
    +0.12
    0.02
    Negative Logits
    arers
    -1.76
    apid
    -1.76
    ^{-\
    -1.76
    rers
    -1.65
    ubicin
    -1.62
    ptions
    -1.61
    phi
    -1.59
    chers
    -1.59
    ots
    -1.51
     inhibitors
    -1.48
    POSITIVE LOGITS
    ↵↵
    4.76
    ↵
    4.76
    ↵
    4.76
    č↵
    4.76
    4.76
    ↵
    4.76
    ↵↵↵
    4.76
    ↵↵
    4.76
    4.76
    ↵  âĢĥ
    4.76
    Activations Density 0.052%

    No Known Activations