© 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. 2-RES-SM
    11. 30375
    Prev
    Next
    INDEX
    Explanations

    references to time periods in the past, specifically the last decade or so

    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
    476
    +0.13
    0.7%
    142
    +0.13
    0.7%
    265
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    239
    +0.13
    0.04
    476
    +0.13
    0.04
    75
    +0.12
    0.03
    Negative Logits
    ability
    -1.83
    chitz
    -1.59
    abilities
    -1.54
    omitempty
    -1.52
     ease
    -1.50
     accordingly
    -1.49
    rVert
    -1.44
    ivas
    -1.38
    igon
    -1.36
    [{
    -1.36
    POSITIVE LOGITS
    »
    2.25
    ↵
    2.00
    ↵
    2.00
    <|outofrange|>
    2.00
    ↵
    2.00
    ↵
    2.00
    č↵
    2.00
    č↵
    2.00
    ↵
    2.00
    2.00
    Activations Density 0.078%

    No Known Activations