© 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. 25591
    Prev
    Next
    INDEX
    Explanations

    terms related to genetics and genomic technologies

    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
    43
    +0.16
    0.9%
    177
    +0.15
    0.8%
    386
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.16
    0.03
    177
    +0.15
    0.02
    271
    +0.13
    0.01
    Negative Logits
    izumab
    -1.63
    fully
    -1.62
    ders
    -1.53
    lando
    -1.51
    midt
    -1.47
    psin
    -1.46
    ETHOD
    -1.45
    beit
    -1.43
    rror
    -1.43
     Redistributions
    -1.42
    POSITIVE LOGITS
    itals
    2.22
    otoxicity
    1.83
    otypic
    1.78
    otoxic
    1.60
    etics
    1.56
    etically
    1.52
    etica
    1.52
    omics
    1.45
    iste
    1.44
    ocide
    1.41
    Activations Density 0.117%

    No Known Activations