© 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. 27565
    Prev
    Next
    INDEX
    Explanations

    terms denoting variability or changes in quantity or quality across different contexts

    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
    196
    +0.14
    0.8%
    268
    +0.13
    0.7%
    375
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    375
    +0.14
    0.02
    268
    +0.13
    0.03
    196
    +0.12
    0.02
    Negative Logits
    ĸ´
    -2.82
    ±
    -2.68
    ·¸
    -2.67
    ĸ
    -2.60
    ¹
    -2.53
    Ĭ
    -2.49
    Į
    -2.47
    IJ
    -2.40
    ģ
    -2.40
    ¿½
    -2.40
    POSITIVE LOGITS
    iated
    2.02
    iates
    1.91
     between
    1.89
    iate
    1.77
     sized
    1.71
    between
    1.70
     across
    1.59
    ely
    1.54
    uous
    1.52
    romycin
    1.48
    Activations Density 0.136%

    No Known Activations