© 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. 27046
    Prev
    Next
    INDEX
    Explanations

    references to measurement units or quantities

    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
    156
    +0.15
    0.8%
    130
    +0.13
    0.7%
    472
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.15
    0.01
    130
    +0.13
    0.02
    245
    +0.12
    0.02
    Negative Logits
    ĻĤ
    -3.65
    ĨĴ
    -3.54
    Ļª
    -3.03
    ¡
    -2.94
    ©
    -2.92
    ¬
    -2.85
    Ĵ
    -2.72
    Ń
    -2.63
    «
    -2.62
    §
    -2.60
    POSITIVE LOGITS
    ters
    1.74
     consists
    1.71
    ature
    1.70
    arily
    1.69
    liness
    1.66
     comprises
    1.59
    rics
    1.58
    aho
    1.58
    aku
    1.57
    enberg
    1.57
    Activations Density 0.144%

    No Known Activations