© 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. 4-RES-SM
    11. 9456
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to experimental methods and protein analysis in scientific research

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    +0.27
    1.6%
    271
    +0.15
    0.9%
    25
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    333
    +0.27
    0.08
    347
    +0.15
    0.10
    136
    +0.14
    -0.04
    Negative Logits
     security
    -1.82
     heels
    -1.74
     fraud
    -1.56
     mistakes
    -1.56
     treasure
    -1.56
     crime
    -1.55
    bie
    -1.53
     teachers
    -1.51
    zes
    -1.51
     puzzle
    -1.49
    POSITIVE LOGITS
    ĻĤ
    4.77
    ij
    4.58
    ·¸
    4.49
    ĭ
    4.47
    Ĺ
    4.34
    ľ
    4.33
    Īĺ
    4.32
    ³
    4.31
    ĨĴ
    4.29
    ¦
    4.25
    Activations Density 1.452%

    No Known Activations