© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 12052
    Prev
    Next
    INDEX
    Explanations

    terms related to lactose and digestive processes

    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
    +0.15
    0.9%
    337
    +0.14
    0.8%
    345
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.15
    0.02
    21
    +0.14
    0.01
    255
    +0.12
    -0.00
    Negative Logits
    nel
    -1.95
    iary
    -1.54
    ventory
    -1.54
    stit
    -1.49
    nae
    -1.46
    tit
    -1.46
    blr
    -1.39
    eting
    -1.36
    ned
    -1.35
    nets
    -1.34
    POSITIVE LOGITS
    ħ
    3.56
    ĥ
    3.24
    Ļ
    3.21
    Ń
    3.04
    ī
    2.96
    «
    2.93
    ĵ
    2.93
    ģ
    2.92
    Ĥ
    2.87
    ©
    2.72
    Activations Density 0.084%

    No Known Activations