© 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. 4-RES-SM
    11. 10649
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "found" and its variations in context

    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
    78
    +0.18
    1.0%
    21
    +0.17
    1.0%
    23
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.18
    0.02
    450
    +0.17
    0.01
    316
    +0.14
    0.02
    Negative Logits
    imization
    -1.38
     gates
    -1.35
     doors
    -1.34
     accelerator
    -1.33
     audience
    -1.31
    ancel
    -1.31
    integration
    -1.31
     outlets
    -1.30
     conventions
    -1.30
     expectations
    -1.28
    POSITIVE LOGITS
     genus
    2.24
     species
    1.90
     extinct
    1.76
     breed
    1.74
     botan
    1.73
     endemic
    1.67
    inae
    1.64
     pathogen
    1.62
    iday
    1.60
    idae
    1.60
    Activations Density 0.068%

    No Known Activations