© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27261
    Prev
    Next
    INDEX
    Explanations

    URLs or web links that start with "com"

    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
    70
    +0.11
    0.6%
    489
    +0.10
    0.6%
    476
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    489
    +0.11
    0.04
    70
    +0.10
    0.04
    476
    +0.10
    0.05
    Negative Logits
     streak
    -1.58
     voluntary
    -1.48
     hereditary
    -1.47
     definite
    -1.47
     *[
    -1.44
     descent
    -1.41
     [[*
    -1.38
     maturation
    -1.38
     transverse
    -1.37
     subtracted
    -1.37
    POSITIVE LOGITS
    room
    2.08
    pieces
    2.00
    ament
    1.84
    poser
    1.80
    ycin
    1.75
    endas
    1.74
    tes
    1.71
     dollars
    1.70
    anks
    1.67
    bels
    1.67
    Activations Density 0.088%

    No Known Activations