© 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. 14967
    Prev
    Next
    INDEX
    Explanations

    specific medical conditions and their risk factors

    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
    156
    +0.18
    1.1%
    306
    +0.14
    0.8%
    505
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.18
    0.01
    87
    +0.14
    0.02
    271
    +0.14
    0.00
    Negative Logits
    )].
    -1.71
    edia
    -1.69
    "].
    -1.64
     tester
    -1.61
     vez
    -1.56
     _________________________________
    -1.54
     thereof
    -1.54
    oslov
    -1.53
    .
    -1.51
     vols
    -1.49
    POSITIVE LOGITS
    »¿
    3.51
    ŀ
    3.22
    ĵ
    3.02
    ĻĤ
    2.97
    »
    2.92
    Ī
    2.84
    Ł
    2.81
    ¼
    2.79
    ķ
    2.75
    ¤
    2.73
    Activations Density 0.082%

    No Known Activations