© 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. 13358
    Prev
    Next
    INDEX
    Explanations

    references to plant-related topics and botanical characteristics

    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
    21
    +0.25
    1.5%
    316
    +0.15
    1.0%
    306
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.25
    0.38
    156
    +0.15
    0.28
    71
    +0.15
    0.26
    Negative Logits
    terest
    -1.88
    ching
    -1.56
    elijk
    -1.43
    apshot
    -1.43
     conversation
    -1.40
    verter
    -1.39
    bed
    -1.39
    binding
    -1.35
    mond
    -1.32
    sizeof
    -1.31
    POSITIVE LOGITS
    osa
    1.52
    osity
    1.49
    ades
    1.41
    ean
    1.32
    ican
    1.32
     elegans
    1.31
    iform
    1.27
    idone
    1.26
    oles
    1.25
    ossa
    1.25
    Activations Density 0.960%

    No Known Activations