© 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. 1-RES-SM
    11. 28905
    Prev
    Next
    INDEX
    Explanations

    specific years and numerical dates

    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
    369
    +0.18
    1.0%
    502
    +0.13
    0.7%
    23
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    477
    +0.18
    0.08
    458
    +0.13
    0.06
    307
    +0.12
    0.06
    Negative Logits
     fence
    -1.78
    ments
    -1.77
    ment
    -1.74
     mindset
    -1.72
    iary
    -1.68
    ulates
    -1.63
    iction
    -1.60
    ismus
    -1.58
     mentality
    -1.57
    resses
    -1.57
    POSITIVE LOGITS
    ĥ½
    3.22
    Ŀ
    3.06
    ħ
    2.97
    ·¸
    2.96
    »
    2.87
    ´
    2.82
    ³
    2.80
    į
    2.80
    Į
    2.78
    Ĵ
    2.78
    Activations Density 0.318%

    No Known Activations