© 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. 25272
    Prev
    Next
    INDEX
    Explanations

    names associated with legal or financial matters

    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
    304
    +0.14
    0.9%
    264
    +0.11
    0.7%
    285
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.14
    0.02
    483
    +0.11
    0.02
    285
    +0.11
    0.02
    Negative Logits
     slightest
    -1.92
     doubt
    -1.72
     meantime
    -1.64
     own
    -1.64
     suspect
    -1.62
     consequence
    -1.59
     behalf
    -1.58
     blame
    -1.55
     hind
    -1.53
     welcome
    -1.52
    POSITIVE LOGITS
    issions
    1.80
    .[]{
    1.71
    ongs
    1.68
    etr
    1.67
    neys
    1.67
    pires
    1.67
    ancer
    1.66
    ettes
    1.64
     (@
    1.64
    etheus
    1.63
    Activations Density 0.063%

    No Known Activations