© 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. 28752
    Prev
    Next
    INDEX
    Explanations

    references to fresh, ripe, or high-quality food items

    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
    156
    +0.19
    1.1%
    362
    +0.17
    1.0%
    163
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.19
    0.03
    163
    +0.17
    0.03
    380
    +0.13
    0.02
    Negative Logits
    unnumbered
    -1.72
    ople
    -1.66
    bserver
    -1.62
    :"){
    -1.60
    ymmetric
    -1.58
    Į
    -1.53
    utes
    -1.52
    OLOR
    -1.51
     Sequence
    -1.51
     Protocol
    -1.50
    POSITIVE LOGITS
    ness
    2.19
    stuff
    1.77
    men
    1.72
    NESS
    1.63
    ettes
    1.63
    neck
    1.62
    yards
    1.61
    ty
    1.59
    man
    1.59
    born
    1.58
    Activations Density 0.140%

    No Known Activations