© 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. 4-RES-SM
    11. 9883
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistics

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    271
    +0.21
    1.2%
    410
    +0.18
    1.0%
    350
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    340
    +0.21
    0.03
    388
    +0.18
    0.02
    410
    +0.14
    0.03
    Negative Logits
     resulted
    -1.57
    alities
    -1.53
     adequately
    -1.53
     therein
    -1.52
     exceeds
    -1.52
     precludes
    -1.51
    ière
    -1.49
     yield
    -1.49
     homeostasis
    -1.48
     permits
    -1.45
    POSITIVE LOGITS
    Ĭ
    4.05
    ı
    3.97
    ¦
    3.94
    ³
    3.78
    ´
    3.78
    Į
    3.75
    ĺ
    3.74
    §
    3.73
    İ
    3.71
    ±
    3.71
    Activations Density 0.062%

    No Known Activations