© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29714
    Prev
    Next
    INDEX
    Explanations

    phrases that signal transactions or purchases

    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
    +0.23
    1.3%
    17
    +0.15
    0.9%
    72
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.23
    -0.03
    420
    +0.15
    0.06
    72
    +0.13
    0.05
    Negative Logits
    idone
    -1.52
    ató
    -1.51
    vist
    -1.49
    ikov
    -1.48
    bio
    -1.48
    arias
    -1.47
    ¯
    -1.47
    µ
    -1.46
    ·
    -1.44
    º
    -1.44
    POSITIVE LOGITS
     Conclusion
    1.88
     your
    1.79
     Campaign
    1.68
     Your
    1.67
     times
    1.61
     Results
    1.51
     Schools
    1.50
     Career
    1.46
     Coach
    1.46
     Parties
    1.43
    Activations Density 2.864%

    No Known Activations