© 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. 2-RES-SM
    11. 9888
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to purchasing or buying

    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
    29
    +0.14
    0.8%
    156
    +0.13
    0.7%
    174
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    29
    +0.14
    0.02
    317
    +0.13
    0.04
    263
    +0.11
    0.04
    Negative Logits
    ĨĴ
    -2.83
    Ń
    -2.65
    ·
    -2.51
    ŀ
    -2.49
    £
    -2.46
    Ł
    -2.43
    Īĺ
    -2.40
    ¾
    -2.36
    ļ
    -2.31
    ©
    -2.31
    POSITIVE LOGITS
     goods
    2.08
     cheaper
    2.01
     grocer
    1.91
     tickets
    1.90
     stocks
    1.79
     cheap
    1.78
     products
    1.73
    eful
    1.68
     items
    1.65
     merchandise
    1.63
    Activations Density 0.307%

    No Known Activations