© 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. 1-RES-SM
    11. 27180
    Prev
    Next
    INDEX
    Explanations

    references to dietary habits and related nutritional topics

    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
    +0.15
    0.9%
    302
    +0.13
    0.8%
    328
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.15
    0.02
    328
    +0.13
    0.02
    361
    +0.10
    0.01
    Negative Logits
     forth
    -1.96
    Ŀ
    -1.83
    -1.76
    -1.76
     ↵
    -1.76
    -1.76
    ↵
    -1.76
    -1.76
    č↵
    -1.76
    -1.76
    POSITIVE LOGITS
    etic
    2.58
    iver
    1.90
    arium
    1.85
    etics
    1.84
    ic
    1.81
    namese
    1.75
    calc
    1.72
    itian
    1.70
    igraph
    1.69
    etica
    1.65
    Activations Density 0.126%

    No Known Activations