© 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. 27505
    Prev
    Next
    INDEX
    Explanations

    language related to software licensing and compliance

    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
    453
    +0.14
    0.8%
    505
    +0.12
    0.7%
    320
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.14
    0.04
    453
    +0.12
    0.02
    333
    +0.11
    0.02
    Negative Logits
    »
    -1.65
    []{
    -1.49
    \]](
    -1.47
     looked
    -1.44
     lapar
    -1.43
     tuned
    -1.42
     shine
    -1.42
     reminded
    -1.41
     Krish
    -1.39
     <-
    -1.38
    POSITIVE LOGITS
    elig
    1.80
    uto
    1.67
    ibilit
    1.60
     lieu
    1.59
    alties
    1.57
    úblic
    1.55
    utation
    1.55
    ENTIAL
    1.55
    mund
    1.54
    ibil
    1.52
    Activations Density 0.204%

    No Known Activations