© 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. 1-RES-SM
    11. 28695
    Prev
    Next
    INDEX
    Explanations

    terms related to odors and olfactory experiences

    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
    369
    +0.16
    0.9%
    321
    +0.12
    0.7%
    59
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.16
    0.03
    410
    +0.12
    0.04
    369
    +0.11
    0.02
    Negative Logits
    ered
    -1.65
    urable
    -1.63
     away
    -1.58
    >();
    -1.49
    angular
    -1.46
     infra
    -1.41
    WHM
    -1.38
    orget
    -1.38
    times
    -1.36
    rifug
    -1.35
    POSITIVE LOGITS
    ī
    4.83
    Ĵ
    4.80
    ¥
    4.55
    º
    4.50
    ¹
    4.43
    Ģ
    4.38
    ĨĴ
    4.32
    į
    4.30
    ľ
    4.29
    ł
    4.29
    Activations Density 0.160%

    No Known Activations