© 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. 27711
    Prev
    Next
    INDEX
    Explanations

    configuration settings related to systems or components

    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
    +0.13
    0.8%
    444
    +0.13
    0.8%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.13
    0.01
    508
    +0.13
    0.01
    356
    +0.12
    0.01
    Negative Logits
    ľ
    -2.14
    ĸ´
    -1.82
    Ĥ
    -1.77
    ĸ
    -1.73
    į
    -1.73
     deceased
    -1.69
    ľĵ
    -1.60
    ¿½
    -1.59
    ught
    -1.57
    ĻĤ
    -1.56
    POSITIVE LOGITS
    iere
    1.95
    arts
    1.69
    éd
    1.64
    ière
    1.59
    ila
    1.58
    works
    1.55
    quart
    1.55
    igan
    1.51
     compared
    1.50
    quist
    1.49
    Activations Density 0.072%

    No Known Activations