© 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. 24613
    Prev
    Next
    INDEX
    Explanations

    programming elements related to importing libraries and handling system functions

    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
    53
    +0.13
    0.8%
    42
    +0.12
    0.7%
    134
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.13
    0.07
    271
    +0.12
    0.01
    17
    +0.12
    0.03
    Negative Logits
    ists
    -1.66
     guys
    -1.56
     chicks
    -1.53
     characters
    -1.52
     fails
    -1.48
    za
    -1.41
     antagonists
    -1.38
     Money
    -1.38
    ony
    -1.35
     advisors
    -1.33
    POSITIVE LOGITS
    Ĥ¬
    1.93
    ŀ
    1.82
    ĨĴ
    1.80
    ½
    1.63
    edom
    1.57
    Ĵ
    1.50
    ¼
    1.48
    ©
    1.44
    ´
    1.44
    handed
    1.43
    Activations Density 0.354%

    No Known Activations