© 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. 1-RES-SM
    11. 25410
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparative analysis or contrasting elements

    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
    23
    +0.20
    1.2%
    478
    +0.15
    0.9%
    350
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    226
    +0.20
    0.03
    20
    +0.15
    0.02
    83
    +0.11
    0.03
    Negative Logits
    ĨĴ
    -2.44
    ¼
    -1.95
    ¶
    -1.93
    º
    -1.70
    ella
    -1.61
    etta
    -1.58
    µ
    -1.58
    ¹
    -1.57
    ¬
    -1.54
    ĭ
    -1.54
    POSITIVE LOGITS
    pired
    1.77
     wisdom
    1.72
    наÑĩ
    1.57
    dern
    1.56
    mathrsfs
    1.47
    fered
    1.47
     fact
    1.46
     opinion
    1.46
    mered
    1.42
    teenth
    1.39
    Activations Density 0.319%

    No Known Activations