© 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. 13628
    Prev
    Next
    INDEX
    Explanations

    narrative details related to health implications and cognitive processes

    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
    306
    +0.20
    1.2%
    21
    +0.12
    0.7%
    316
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.20
    0.05
    447
    +0.12
    0.07
    450
    +0.11
    0.01
    Negative Logits
    ascii
    -1.66
    ipment
    -1.65
    cester
    -1.57
     everybody
    -1.53
     customs
    -1.49
    ourier
    -1.49
    arum
    -1.47
     pictures
    -1.47
     ordinary
    -1.45
    olor
    -1.44
    POSITIVE LOGITS
     compelling
    1.96
     incent
    1.78
     strategies
    1.76
     fueled
    1.68
     empower
    1.64
     exacerbated
    1.62
     goals
    1.62
     hypothesized
    1.61
     motiv
    1.61
     heightened
    1.61
    Activations Density 1.565%

    No Known Activations