© 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. 10880
    Prev
    Next
    INDEX
    Explanations

    phrases related to combinations or integrations of elements or concepts

    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
    9
    +0.22
    1.2%
    194
    +0.13
    0.7%
    225
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.22
    0.03
    82
    +0.13
    0.03
    500
    +0.12
    0.03
    Negative Logits
    men
    -1.55
    лÑı
    -1.49
    erd
    -1.47
    respect
    -1.43
    let
    -1.41
    ours
    -1.36
    ars
    -1.35
    oddsidemargin
    -1.35
    why
    -1.34
    nail
    -1.34
    POSITIVE LOGITS
    inib
    1.96
     therapy
    1.91
     thereof
    1.81
    ronic
    1.77
     with
    1.76
     effect
    1.76
     therapies
    1.70
     between
    1.65
    amine
    1.65
     use
    1.65
    Activations Density 0.452%

    No Known Activations