© 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. 2-RES-SM
    11. 12904
    Prev
    Next
    INDEX
    Explanations

    questions related to challenges and outcomes in various situations

    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
    263
    +0.22
    1.3%
    176
    +0.14
    0.8%
    161
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.22
    0.10
    176
    +0.14
    0.09
    500
    +0.14
    0.07
    Negative Logits
    ĻĤ
    -5.37
    į
    -5.09
    Ļª
    -4.96
    ģ
    -4.86
    ĸ
    -4.84
    º
    -4.80
    Ļ
    -4.78
    Ħ
    -4.78
    ¨
    -4.77
    Īĺ
    -4.74
    POSITIVE LOGITS
    forth
    1.85
    again
    1.70
     again
    1.64
    iew
    1.56
     steadily
    1.45
    gaard
    1.42
     markets
    1.37
     ladies
    1.35
    girl
    1.34
     dishes
    1.33
    Activations Density 1.333%

    No Known Activations