© 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. 27349
    Prev
    Next
    INDEX
    Explanations

    mentions of days, particularly "Sunday" and "Saturday"

    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
    +0.16
    0.9%
    287
    +0.11
    0.6%
    336
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.16
    0.03
    226
    +0.11
    0.03
    346
    +0.11
    0.02
    Negative Logits
    ĺ
    -3.53
    ¬
    -3.53
    ŀ
    -3.31
    ·¸
    -3.30
    ħ
    -3.26
    Ķ
    -3.25
    ĥ½
    -3.22
    ¶
    -3.18
    Ŀ
    -3.15
    ĩ
    -3.14
    POSITIVE LOGITS
     Morning
    2.14
     morning
    1.89
     prayers
    1.85
    vist
    1.77
    dream
    1.68
     afternoon
    1.66
     Evening
    1.65
     Night
    1.57
    oda
    1.53
    ved
    1.53
    Activations Density 0.087%

    No Known Activations