© 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. 25250
    Prev
    Next
    INDEX
    Explanations

    words that contain the character "é"

    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
    410
    +0.14
    0.8%
    393
    +0.13
    0.7%
    111
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.14
    0.02
    380
    +0.13
    0.02
    410
    +0.13
    0.02
    Negative Logits
      ↵
    -1.96
     humans
    -1.88
    >&
    -1.78
    ffected
    -1.62
     affected
    -1.54
    )$)
    -1.52
    >$
    -1.51
     flowering
    -1.49
     east
    -1.47
     sexes
    -1.47
    POSITIVE LOGITS
    rico
    1.83
    tico
    1.67
    ven
    1.64
    cco
    1.62
     Awards
    1.61
    nel
    1.59
    ral
    1.54
    amon
    1.53
    vist
    1.53
    lic
    1.52
    Activations Density 0.059%

    No Known Activations