© 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 EvalsExportsAPI 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. 11037
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular and molecular biology

    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
    148
    +0.13
    0.7%
    156
    +0.13
    0.7%
    253
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.01
    47
    +0.13
    0.01
    275
    +0.12
    0.01
    Negative Logits
    ureus
    -1.78
     Month
    -1.60
    iki
    -1.58
    LEASE
    -1.52
    poons
    -1.51
    ikan
    -1.47
    iei
    -1.44
    aucoup
    -1.41
    owing
    -1.41
    ursuant
    -1.41
    POSITIVE LOGITS
    ¤
    3.02
    Ń
    2.60
    º
    2.53
    °
    2.53
    ĺ
    2.52
    ¿
    2.51
    ł
    2.50
    Ł
    2.49
    ĵ
    2.47
    ity
    2.46
    Activations Density 0.024%

    No Known Activations