© 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. 2-RES-SM
    11. 31958
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to data transmission, technology applications, and the production of materials

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.21
    1.2%
    207
    +0.12
    0.7%
    186
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.21
    0.04
    418
    +0.12
    -0.02
    403
    +0.12
    0.04
    Negative Logits
     result
    -1.88
    «
    -1.74
    ı
    -1.59
    Ĺ
    -1.58
    "_
    -1.58
     results
    -1.58
    Į
    -1.56
    ª
    -1.56
     memo
    -1.55
    ij
    -1.51
    POSITIVE LOGITS
    etin
    1.67
    FPar
    1.65
    );\
    1.61
    etheus
    1.54
    forge
    1.52
    aceutics
    1.49
    utively
    1.47
    )):
    1.47
    abo
    1.44
    bane
    1.44
    Activations Density 1.227%

    No Known Activations