© 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 EvalsExportsinterp-engineNEWAPI 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. 12673
    Prev
    Next
    INDEX
    Explanations

    references to night and nighttime activities

    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
    477
    +0.16
    0.9%
    287
    +0.14
    0.8%
    56
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.16
    0.05
    56
    +0.14
    0.01
    287
    +0.13
    0.04
    Negative Logits
    Ŀ
    -4.28
    ľĵ
    -4.24
    ĥ
    -4.24
    Ĩ
    -4.16
    ĺ
    -4.14
    ĸ
    -4.10
    ķ
    -4.09
    Īĺ
    -4.05
    Ļ
    -4.00
    ·¸
    -3.98
    POSITIVE LOGITS
    ingale
    3.06
    mares
    2.62
    mare
    2.14
    time
    2.08
    noon
    1.94
    club
    1.94
    fires
    1.84
    lights
    1.81
    sky
    1.74
     Lights
    1.74
    Activations Density 0.214%

    No Known Activations