© 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. 1-RES-SM
    11. 26158
    Prev
    Next
    INDEX
    Explanations

    terms related to network packets

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.21
    1.3%
    490
    +0.14
    0.8%
    18
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.21
    0.02
    156
    +0.14
    0.02
    86
    +0.11
    0.02
    Negative Logits
    ·
    -2.28
    ĥ½
    -2.14
    Ļª
    -2.02
    estly
    -1.96
    ³
    -1.89
    ´
    -1.89
    ľĵ
    -1.86
    Ĥ¬
    -1.83
    ĸ´
    -1.83
    ·¸
    -1.81
    POSITIVE LOGITS
    ahead
    1.87
    GS
    1.85
    ination
    1.83
    maker
    1.80
    mouth
    1.77
    info
    1.74
    agram
    1.72
    ups
    1.71
    ncbi
    1.71
    ellation
    1.71
    Activations Density 0.175%

    No Known Activations