© 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 EvalsExportsinterp-engineNEWAPI 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. 14007
    Prev
    Next
    INDEX
    Explanations

    phrases or actions related to events and situations that are imminent or expected to happen soon

    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
    50
    +0.13
    0.7%
    184
    +0.13
    0.7%
    0
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    339
    +0.13
    0.04
    15
    +0.13
    0.08
    0
    +0.12
    0.05
    Negative Logits
    ĥ½
    -3.67
    ¢
    -3.16
    ³
    -3.16
    Īĺ
    -2.95
    §
    -2.94
    į
    -2.93
    ľĵ
    -2.86
    ŀ
    -2.82
    ·
    -2.80
    ļ
    -2.80
    POSITIVE LOGITS
     tomorrow
    2.24
     soon
    2.20
     ahead
    1.93
     next
    1.93
     off
    1.86
     closer
    1.84
     up
    1.83
     forth
    1.81
     out
    1.73
    soon
    1.72
    Activations Density 0.880%

    No Known Activations