© 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. 2-RES-SM
    11. 28529
    Prev
    Next
    INDEX
    Explanations

    words related to flavor and taste preferences

    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
    214
    +0.14
    0.8%
    412
    +0.12
    0.7%
    127
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.14
    0.02
    386
    +0.12
    0.01
    127
    +0.12
    0.03
    Negative Logits
    Ł
    -2.15
    ´
    -1.75
    ITED
    -1.74
    ¾
    -1.68
    onds
    -1.66
    ypse
    -1.62
    Ĭ
    -1.60
    ¦
    -1.59
    µ
    -1.58
    UIC
    -1.54
    POSITIVE LOGITS
     buds
    1.94
    bud
    1.82
    root
    1.75
    bank
    1.67
    iness
    1.67
    wart
    1.43
    consin
    1.40
     approving
    1.40
    ^[
    1.40
    ual
    1.37
    Activations Density 0.225%

    No Known Activations