© 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. 2-RES-SM
    11. 27228
    Prev
    Next
    INDEX
    Explanations

    aspects related to acknowledgments and gratitude in academic or collaborative contexts

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    326
    +0.17
    0.9%
    252
    +0.12
    0.7%
    292
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    252
    +0.17
    0.02
    326
    +0.12
    0.01
    21
    +0.11
    0.01
    Negative Logits
     dye
    -1.57
     store
    -1.43
     rentals
    -1.40
    ces
    -1.40
     storing
    -1.38
     storage
    -1.38
     vez
    -1.37
    odor
    -1.30
     dyes
    -1.30
     stored
    -1.29
    POSITIVE LOGITS
    ĥ½
    2.07
    ŀ
    2.02
    »¿
    1.93
    abstract
    1.83
    ´
    1.69
    ³
    1.64
    ¦
    1.59
    bibliography
    1.57
    adays
    1.55
    Simplify
    1.51
    Activations Density 0.173%

    No Known Activations