© 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. 27447
    Prev
    Next
    INDEX
    Explanations

    instances of the word "DO" in various contexts

    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
    369
    +0.18
    1.0%
    183
    +0.12
    0.7%
    243
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.18
    0.02
    105
    +0.12
    0.01
    130
    +0.11
    0.01
    Negative Logits
    iated
    -1.75
    matically
    -1.74
    noreply
    -1.63
    ize
    -1.63
    elves
    -1.62
    ly
    -1.61
    liest
    -1.59
    oscopy
    -1.57
    acial
    -1.51
    ophore
    -1.50
    POSITIVE LOGITS
    zens
    1.78
    STIT
    1.75
    º
    1.74
     Redistributions
    1.71
    CTYPE
    1.67
    ctors
    1.66
    ES
    1.64
     NOT
    1.62
    herty
    1.60
    FIL
    1.60
    Activations Density 0.083%

    No Known Activations