© 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. 13028
    Prev
    Next
    INDEX
    Explanations

    terms related to health, nutrition, and food sources

    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
    156
    +0.40
    2.4%
    186
    +0.14
    0.9%
    321
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    45
    +0.40
    0.05
    186
    +0.14
    0.05
    227
    +0.10
    0.07
    Negative Logits
     hers
    -1.85
     yours
    -1.80
    ETHOD
    -1.64
     '</
    -1.60
    lickr
    -1.54
    jour
    -1.54
     theirs
    -1.52
    FFIR
    -1.50
     ours
    -1.48
    leep
    -1.44
    POSITIVE LOGITS
     and
    1.73
    -,
    1.64
     origin
    1.61
    -
    1.61
     or
    1.56
     etc
    1.54
     bases
    1.53
    âĢij
    1.50
     controlled
    1.47
     categories
    1.36
    Activations Density 2.235%

    No Known Activations