© 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. 4-RES-SM
    11. 9618
    Prev
    Next
    INDEX
    Explanations

    possessive forms of nouns

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    156
    +0.26
    1.6%
    21
    +0.17
    1.1%
    348
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    145
    +0.26
    0.05
    137
    +0.17
    0.06
    382
    +0.14
    0.02
    Negative Logits
    ĥ½
    -1.89
    ening
    -1.70
    ľ
    -1.68
    -1.67
    ↵
    -1.67
    ↵
    -1.67
    ↵
    -1.67
    ↵            ↵
    -1.67
    ↵
    -1.67
    ↵
    -1.67
    POSITIVE LOGITS
     sake
    2.25
     own
    1.82
     footsteps
    1.81
     feet
    1.80
     paradise
    1.68
    chaft
    1.67
     Corner
    1.64
     perspective
    1.63
     eyes
    1.63
     birthday
    1.62
    Activations Density 0.336%

    No Known Activations