© 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. 27494
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data related to sports and health metrics

    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
    153
    +0.14
    0.8%
    369
    +0.12
    0.7%
    307
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.14
    0.05
    203
    +0.12
    0.05
    436
    +0.11
    0.06
    Negative Logits
    Ĩ
    -2.87
    ĺ
    -2.71
    ¼
    -2.47
    ½
    -2.39
    ©
    -2.34
    »¿
    -2.31
    °
    -2.27
    ĥ
    -2.23
    ±
    -2.22
    Ĥ
    -2.21
    POSITIVE LOGITS
     alike
    2.01
    oint
    1.71
     thereafter
    1.71
    th
    1.71
     added
    1.68
    inks
    1.62
    %"
    1.57
     further
    1.52
    itudes
    1.52
     additional
    1.52
    Activations Density 0.364%

    No Known Activations