© 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. 12457
    Prev
    Next
    INDEX
    Explanations

    words related to dietary supplements and nutritional components

    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
    306
    +0.13
    0.7%
    307
    +0.13
    0.7%
    86
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    134
    +0.13
    0.06
    369
    +0.13
    0.02
    86
    +0.12
    0.03
    Negative Logits
     oxidase
    -1.59
    equation
    -1.44
     judge
    -1.43
     correctly
    -1.41
     course
    -1.40
     ^{
    -1.38
     collision
    -1.36
     reviewers
    -1.35
     errors
    -1.35
     pesticides
    -1.31
    POSITIVE LOGITS
    Ļ
    2.55
    ¿
    2.32
    ´
    2.23
    Ĵ
    2.21
    ĺ
    2.14
    ŀ
    2.14
    ³
    2.11
    º
    2.10
    ª
    2.09
    Ń
    2.09
    Activations Density 0.356%

    No Known Activations