© 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. 14703
    Prev
    Next
    INDEX
    Explanations

    terms related to blood and immune system cells

    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
    348
    +0.19
    1.1%
    217
    +0.13
    0.7%
    78
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.19
    0.02
    7
    +0.13
    0.01
    440
    +0.13
    0.01
    Negative Logits
    orems
    -2.00
    chool
    -1.70
    boards
    -1.68
    ylan
    -1.60
    tons
    -1.60
    due
    -1.58
    owing
    -1.54
     IEEE
    -1.54
    bib
    -1.53
    ylene
    -1.52
    POSITIVE LOGITS
     phag
    2.21
     progenitors
    2.16
     activation
    2.08
     infiltration
    2.08
     cells
    2.05
     leukocytes
    2.04
     count
    1.99
     progenitor
    1.99
     recruitment
    1.98
     counts
    1.97
    Activations Density 0.082%

    No Known Activations