© 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. 11195
    Prev
    Next
    INDEX
    Explanations

    references to social and political dynamics

    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
    374
    +0.11
    0.6%
    156
    +0.10
    0.6%
    105
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.11
    0.04
    186
    +0.10
    0.07
    149
    +0.10
    0.07
    Negative Logits
    ¼
    -2.61
    º
    -2.49
    ¯
    -2.29
    Į
    -2.12
    ¤
    -2.11
    ¹
    -2.08
    Ĭ
    -2.02
    ³
    -2.00
    ·
    -2.00
    ij
    -2.00
    POSITIVE LOGITS
     than
    9.31
    than
    7.73
    Than
    6.51
     Than
    5.46
     compared
    3.48
     besides
    1.97
     versus
    1.97
     fewer
    1.93
     quanto
    1.88
     richer
    1.84
    Activations Density 1.923%

    No Known Activations