© 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. 1-RES-SM
    11. 26596
    Prev
    Next
    INDEX
    Explanations

    references to financial or pension-related terms and specific names in a legal or financial context

    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
    174
    +0.17
    1.0%
    350
    +0.14
    0.8%
    466
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    174
    +0.17
    0.06
    71
    +0.14
    0.06
    321
    +0.13
    0.04
    Negative Logits
    ¼
    -2.77
    º
    -2.55
    ·
    -2.34
    ĥ½
    -2.25
    Ń
    -2.24
    ĵ
    -2.13
    ©
    -2.12
    Īĺ
    -2.07
    «
    -2.07
    £
    -2.05
    POSITIVE LOGITS
    ione
    1.65
    onte
    1.61
    folio
    1.61
    inte
    1.56
    works
    1.54
    uet
    1.54
    etary
    1.52
    ioni
    1.51
    aintiff
    1.49
    cie
    1.47
    Activations Density 0.384%

    No Known Activations