© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 4-RES-SM
    6. 11911
    Prev
    Next
    INDEX
    Explanations

    terms related to biological pathways and cancer research

    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
    168
    +0.15
    0.9%
    203
    +0.14
    0.8%
    240
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.15
    0.03
    203
    +0.14
    0.02
    47
    +0.12
    0.03
    Negative Logits
     cloth
    -2.23
     toilet
    -1.94
     liner
    -1.88
     Ethiopia
    -1.87
     garment
    -1.87
     Peru
    -1.84
     sanitation
    -1.81
     Ecuador
    -1.79
     san
    -1.76
     disposable
    -1.75
    POSITIVE LOGITS
     phosphorylation
    3.64
     kinases
    3.48
     phosphory
    3.46
     kinase
    3.30
     signaling
    3.14
     phosphorylated
    3.13
     ERK
    3.12
    phosphory
    2.99
     MAPK
    2.94
     tyrosine
    2.90
    Activations Density 0.282%

    No Known Activations