© 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. 25746
    Prev
    Next
    INDEX
    Explanations

    licenses or documentation related to software and projects

    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
    329
    +0.13
    0.7%
    139
    +0.12
    0.7%
    478
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    329
    +0.13
    0.04
    289
    +0.12
    0.02
    416
    +0.12
    0.03
    Negative Logits
    Intent
    -1.69
    rolet
    -1.58
    position
    -1.50
    yrs
    -1.50
    uchar
    -1.43
    ulse
    -1.43
     firing
    -1.42
     liking
    -1.41
    tons
    -1.40
    ms
    -1.40
    POSITIVE LOGITS
    Ļª
    3.21
    ŀ
    2.77
    ±
    2.69
    ĻĤ
    2.67
    IJ
    2.62
    ĸ´
    2.57
    «
    2.57
    Ģ
    2.54
    ĨĴ
    2.52
    ´
    2.50
    Activations Density 0.380%

    No Known Activations