© 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. 29774
    Prev
    Next
    INDEX
    Explanations

    phrases indicating curiosity or interest

    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
    365
    +0.13
    0.7%
    505
    +0.11
    0.6%
    221
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    38
    +0.13
    0.02
    372
    +0.11
    0.01
    365
    +0.11
    0.02
    Negative Logits
    ĻĤ
    -2.82
    Ĵ
    -2.57
    ĨĴ
    -2.45
    Īĺ
    -2.37
    ¿½
    -2.18
    Ł
    -2.16
    į
    -2.02
    IJ
    -2.00
    ı
    -2.00
    Į
    -1.89
    POSITIVE LOGITS
    edly
    2.29
    ively
    2.02
    iary
    2.00
    ality
    1.98
    alities
    1.84
    als
    1.79
     accru
    1.70
    ally
    1.69
    holder
    1.61
     area
    1.60
    Activations Density 0.164%

    No Known Activations