© 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. 2-RES-SM
    11. 31297
    Prev
    Next
    INDEX
    Explanations

    terms related to heart failure and associated medical conditions

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.20
    1.2%
    387
    +0.13
    0.8%
    508
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.20
    0.01
    52
    +0.13
    0.03
    434
    +0.11
    0.04
    Negative Logits
     grain
    -1.54
    ieurs
    -1.52
     DISCLAIM
    -1.47
     laundry
    -1.38
    &=&
    -1.36
     yourselves
    -1.34
     ÃĤ
    -1.29
    ]=
    -1.28
    &=&\
    -1.28
     iodine
    -1.27
    POSITIVE LOGITS
    àµį
    1.90
    à±į
    1.86
    clerosis
    1.85
    resis
    1.82
    à±ģ
    1.73
    à¯ģ
    1.71
    ember
    1.61
    insula
    1.58
    àµ
    1.57
    ennis
    1.53
    Activations Density 0.429%

    No Known Activations