© 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. 4-RES-SM
    11. 13121
    Prev
    Next
    INDEX
    Explanations

    anticipation and planning for future events

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    397
    +0.19
    1.1%
    9
    +0.12
    0.7%
    370
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.19
    0.09
    99
    +0.12
    0.07
    397
    +0.11
    0.06
    Negative Logits
    ·¸
    -2.92
    ĻĤ
    -2.90
    Ļª
    -2.88
    Ĵ
    -2.84
    Ń
    -2.77
    į
    -2.73
    ŀ
    -2.71
    Ĭ
    -2.57
    IJ
    -2.56
    ¿
    -2.56
    POSITIVE LOGITS
     2021
    2.39
     if
    2.34
     2020
    2.28
     unless
    2.18
     anytime
    2.07
     tomorrow
    2.07
     anyway
    1.98
     sooner
    1.83
     2030
    1.83
     soon
    1.82
    Activations Density 2.002%

    No Known Activations