© 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. 26454
    Prev
    Next
    INDEX
    Explanations

    HTML or XML markup elements and structure

    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
    111
    +0.18
    1.0%
    478
    +0.18
    1.0%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.18
    0.13
    271
    +0.18
    0.06
    156
    +0.12
    0.06
    Negative Logits
    ]{}.
    -1.68
     [(\[
    -1.51
    .’”
    -1.48
     distribution
    -1.46
    ère
    -1.44
     unaffected
    -1.40
    .[]{
    -1.39
    ."""
    -1.39
     issue
    -1.39
     adapted
    -1.39
    POSITIVE LOGITS
    ĻĤ
    3.29
    ĨĴ
    3.24
    Ļª
    3.15
    ¼
    3.01
    ¾
    2.99
    ½
    2.92
    ¸
    2.84
    ĩ
    2.82
    Īĺ
    2.79
    «
    2.73
    Activations Density 0.133%

    No Known Activations