© 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. 28008
    Prev
    Next
    INDEX
    Explanations

    programming code related to data management and system configurations

    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
    307
    +0.14
    0.8%
    143
    +0.14
    0.8%
    50
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    143
    +0.14
    0.09
    50
    +0.14
    0.08
    307
    +0.14
    0.08
    Negative Logits
    $^{-
    -1.87
     \%
    -1.68
     anest
    -1.67
     retrograde
    -1.66
    mathchoice
    -1.57
     [(\[
    -1.56
    ycin
    -1.54
    .|
    -1.51
    ;\;\
    -1.48
     luminal
    -1.45
    POSITIVE LOGITS
    ¹
    2.74
    »
    2.55
    ¾
    2.40
    ¶
    2.39
    ±
    2.37
    Ģ
    2.37
    Ł
    2.33
    <|outofrange|>
    2.29
    ↵  ³³³
    2.29
    č↵
    2.29
    Activations Density 1.114%

    No Known Activations