© 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. 12393
    Prev
    Next
    INDEX
    Explanations

    terms related to cancer and tumor biology

    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
    189
    +0.14
    0.8%
    333
    +0.13
    0.7%
    440
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.14
    0.03
    333
    +0.13
    0.02
    440
    +0.10
    0.01
    Negative Logits
     vez
    -1.67
     alia
    -1.60
     rpm
    -1.52
    ynaptic
    -1.51
     Eliot
    -1.50
     muddy
    -1.46
    sible
    -1.42
     Prayer
    -1.40
     IOException
    -1.40
     adjustable
    -1.40
    POSITIVE LOGITS
    ous
    2.42
     chemotherapy
    2.25
     stem
    2.21
     risk
    2.13
     cells
    2.12
     patients
    2.11
     incidence
    2.10
     mellitus
    2.07
     malignancy
    2.07
     survivors
    2.07
    Activations Density 0.071%

    No Known Activations