© 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 EvalsExportsinterp-engineNEWAPI 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. 24659
    Prev
    Next
    INDEX
    Explanations

    technical terms and library references related to Android development

    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
    397
    +0.13
    0.7%
    116
    +0.12
    0.6%
    174
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    54
    +0.13
    0.03
    214
    +0.12
    0.01
    312
    +0.11
    0.02
    Negative Logits
    ([]
    -1.62
    AtA
    -1.55
    aire
    -1.53
    iji
    -1.52
    ovir
    -1.50
    oto
    -1.47
    {}
    -1.47
    cards
    -1.45
    ons
    -1.44
    ()[
    -1.43
    POSITIVE LOGITS
    ĥ½
    1.61
    Ļª
    1.58
     APPEALS
    1.53
     degeneracy
    1.44
     State
    1.41
    __)
    1.39
     OC
    1.38
    Ģ
    1.38
     chemistry
    1.35
     susceptibility
    1.35
    Activations Density 0.193%

    No Known Activations