© 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. 27783
    Prev
    Next
    INDEX
    Explanations

    sentences with specific date and time information

    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
    76
    +0.11
    0.6%
    193
    +0.10
    0.5%
    176
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    303
    +0.11
    0.02
    289
    +0.10
    0.01
    457
    +0.10
    0.02
    Negative Logits
    ĸ
    -1.71
    ķ
    -1.64
    iller
    -1.54
     scav
    -1.52
    derer
    -1.50
    saving
    -1.50
     sacrifice
    -1.48
     namespace
    -1.47
     owning
    -1.46
     encaps
    -1.46
    POSITIVE LOGITS
    plete
    1.47
    etine
    1.47
    äsident
    1.37
     nods
    1.36
    ricular
    1.35
    obbsee
    1.34
     doubles
    1.28
     tonight
    1.28
     jog
    1.28
    ugu
    1.27
    Activations Density 0.142%

    No Known Activations