© 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. 11267
    Prev
    Next
    INDEX
    Explanations

    specific time periods, dates, and seasonal references

    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
    452
    +0.13
    0.7%
    80
    +0.12
    0.7%
    315
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    452
    +0.13
    0.03
    427
    +0.12
    0.05
    80
    +0.12
    0.02
    Negative Logits
    ĸ
    -3.88
    ģ
    -3.82
    ¢
    -3.82
    ĥ
    -3.61
    ķ
    -3.57
    ĵ
    -3.57
    ŀ
    -3.55
    ·¸
    -3.55
    Ģ
    -3.54
    ¸
    -3.52
    POSITIVE LOGITS
     April
    4.00
     June
    3.91
     February
    3.88
     December
    3.87
     July
    3.84
     October
    3.81
     September
    3.80
     November
    3.77
     March
    3.77
     August
    3.76
    Activations Density 0.495%

    No Known Activations