© 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. 14717
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions related to blood circulation and cardiovascular functions

    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
    185
    +0.11
    0.6%
    336
    +0.11
    0.6%
    308
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.11
    0.04
    11
    +0.11
    0.03
    293
    +0.11
    0.02
    Negative Logits
     axe
    -1.81
     Tut
    -1.76
     knight
    -1.75
     knights
    -1.67
     scars
    -1.62
     homework
    -1.56
     Surviv
    -1.55
     loci
    -1.54
     repr
    -1.53
     Attribute
    -1.51
    POSITIVE LOGITS
     fluid
    3.21
     fluids
    2.99
     flow
    2.88
     Flow
    2.81
     flows
    2.74
     pumping
    2.70
     pumps
    2.66
     pump
    2.63
     flowed
    2.54
     inflow
    2.53
    Activations Density 0.754%

    No Known Activations