© 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. 27252
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and companies

    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
    410
    +0.16
    0.9%
    466
    +0.14
    0.8%
    59
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.16
    0.06
    59
    +0.14
    0.03
    369
    +0.14
    0.02
    Negative Logits
    bbe
    -1.71
    shore
    -1.66
     morning
    -1.55
    ais
    -1.52
    arer
    -1.50
    ays
    -1.50
     closest
    -1.48
     handler
    -1.47
     observer
    -1.47
     af
    -1.46
    POSITIVE LOGITS
    Ĭ
    1.81
    jiang
    1.79
    İ
    1.76
    ĸ
    1.65
    oslav
    1.63
    ollah
    1.62
    ¾
    1.58
    ¢
    1.56
    nai
    1.56
    ulus
    1.54
    Activations Density 0.252%

    No Known Activations