© 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. 28651
    Prev
    Next
    INDEX
    Explanations

    instances of the word "is."

    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
    225
    +0.14
    0.8%
    169
    +0.13
    0.7%
    452
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.14
    0.00
    24
    +0.13
    0.00
    23
    +0.13
    0.00
    Negative Logits
    es
    -1.55
    transcript
    -1.44
     sill
    -1.37
     alarm
    -1.36
     chill
    -1.34
     Mayo
    -1.32
     lime
    -1.31
     dose
    -1.29
    ers
    -1.28
    s
    -1.28
    POSITIVE LOGITS
    optera
    1.87
    rolet
    1.68
    urop
    1.61
    ETHOD
    1.58
    schen
    1.52
    ”:
    1.49
    }$:
    1.48
    PLIED
    1.48
    ksi
    1.46
     brethren
    1.44
    Activations Density 0.000%

    No Known Activations