© 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. 26235
    Prev
    Next
    INDEX
    Explanations

    references to time-related phrases indicating past 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/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
    163
    +0.11
    0.6%
    474
    +0.11
    0.6%
    268
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.11
    0.05
    475
    +0.11
    0.04
    459
    +0.11
    0.04
    Negative Logits
    ²
    -2.75
    Ĥ
    -2.49
    ĺ
    -2.48
    ´
    -2.37
    Ń
    -2.36
    ª
    -2.33
    ī
    -2.31
    µ
    -2.31
    ĸ
    -2.31
    Ħ
    -2.29
    POSITIVE LOGITS
     anniversary
    1.51
    thood
    1.51
    iversary
    1.50
    tain
    1.44
     fuck
    1.41
    ACH
    1.39
    IGHT
    1.36
    Ä
    1.35
    OVE
    1.34
    tah
    1.34
    Activations Density 0.536%

    No Known Activations