© 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. 28056
    Prev
    Next
    INDEX
    Explanations

    phrases related to future events and planning

    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
    23
    +0.17
    0.9%
    353
    +0.12
    0.7%
    70
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.16
    478
    +0.12
    0.00
    240
    +0.11
    -0.04
    Negative Logits
    ulates
    -1.61
    hematic
    -1.57
    és
    -1.51
    uit
    -1.45
    arios
    -1.44
    ENTS
    -1.42
    ución
    -1.42
    iquity
    -1.42
    landers
    -1.39
    erville
    -1.37
    POSITIVE LOGITS
     heartbeat
    1.66
     freeze
    1.65
     restart
    1.64
    acknow
    1.59
     2021
    1.56
     trigger
    1.55
     lock
    1.46
     defer
    1.46
    shut
    1.46
     2020
    1.46
    Activations Density 2.824%

    No Known Activations