© 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. 1-RES-SM
    11. 25700
    Prev
    Next
    INDEX
    Explanations

    technical specifications and numerical data related to devices

    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
    43
    +0.15
    0.8%
    343
    +0.13
    0.7%
    243
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.15
    0.06
    136
    +0.13
    -0.02
    425
    +0.12
    0.05
    Negative Logits
    ko
    -1.48
    giving
    -1.47
    kt
    -1.47
     longer
    -1.44
    oting
    -1.43
    dz
    -1.42
    ears
    -1.41
    woke
    -1.39
    parent
    -1.38
    kot
    -1.37
    POSITIVE LOGITS
     albicans
    2.38
     elegans
    2.11
    ulent
    1.75
    ++
    1.58
    urities
    1.58
     ranks
    1.58
    innati
    1.57
    enberg
    1.56
     reductase
    1.56
    inical
    1.54
    Activations Density 1.014%

    No Known Activations