© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10891
    Prev
    Next
    INDEX
    Explanations

    actions related to dealing with responsibilities and tasks

    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
    +0.23
    1.3%
    186
    +0.15
    0.9%
    156
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.23
    0.16
    323
    +0.15
    0.06
    148
    +0.14
    0.02
    Negative Logits
    Ŀ
    -2.43
    ŀ
    -2.30
    §
    -2.29
    ľ
    -2.20
    ĨĴ
    -2.19
    ¯
    -2.12
    ¹
    -2.10
    į
    -2.08
    ij
    -2.07
    İ
    -2.06
    POSITIVE LOGITS
    ishly
    2.03
    ify
    1.86
    zilla
    1.78
     retard
    1.76
    ually
    1.67
    ably
    1.59
    worm
    1.56
    rypt
    1.53
    kered
    1.52
    ically
    1.51
    Activations Density 1.709%

    No Known Activations