© 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. 31854
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to cancer biology and cellular mechanisms

    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
    47
    +0.13
    0.7%
    503
    +0.12
    0.7%
    43
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.13
    0.08
    134
    +0.12
    0.07
    474
    +0.11
    0.05
    Negative Logits
     tutorial
    -1.70
     flaw
    -1.66
     keyboard
    -1.64
    >&
    -1.62
    msgstr
    -1.61
    optional
    -1.52
     camera
    -1.51
     session
    -1.50
     interview
    -1.48
     rehearing
    -1.48
    POSITIVE LOGITS
    ł
    4.09
    Īĺ
    4.08
    ¿
    3.84
    ¾
    3.82
    ¦
    3.79
    Ĩ
    3.78
    ´
    3.76
    ĻĤ
    3.69
    »
    3.67
    ¨
    3.64
    Activations Density 0.465%

    No Known Activations