© 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 EvalsExportsAPI 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. 27643
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions related to excellence and quality

    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
    118
    +0.12
    0.7%
    444
    +0.12
    0.7%
    68
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    118
    +0.12
    0.02
    68
    +0.12
    0.02
    444
    +0.12
    0.02
    Negative Logits
    »¿
    -3.10
    ·¸
    -2.45
    ĸ´
    -2.41
    İ
    -2.37
    Ĥ
    -2.33
    ¾
    -2.33
    ĸ
    -2.29
    ĻĤ
    -2.29
    ĨĴ
    -2.28
    Ĭ
    -2.28
    POSITIVE LOGITS
    ings
    2.34
    horn
    1.88
    ipt
    1.81
    ungen
    1.81
    aires
    1.79
    wagen
    1.78
    icense
    1.72
    hart
    1.72
    baum
    1.71
    inux
    1.67
    Activations Density 0.131%

    No Known Activations