© 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. 1-RES-SM
    11. 26339
    Prev
    Next
    INDEX
    Explanations

    the concept of "entirety" or "wholeness" in various contexts

    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
    362
    +0.18
    1.0%
    19
    +0.12
    0.7%
    502
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.18
    0.03
    19
    +0.12
    0.02
    188
    +0.12
    0.02
    Negative Logits
     criterion
    -1.48
     confirmation
    -1.42
     Analy
    -1.40
    metric
    -1.39
     certification
    -1.39
     Advance
    -1.36
    ractive
    -1.35
     cutoff
    -1.34
    rers
    -1.34
    abad
    -1.33
    POSITIVE LOGITS
    ¿½
    2.90
    ķ
    2.74
    ¼
    2.61
    º
    2.59
    ·¸
    2.54
    ¸
    2.51
    2.48
    ↵
    2.48
    č↵č↵
    2.48
    ↵
    2.48
    Activations Density 0.042%

    No Known Activations