© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 27242
    Prev
    Next
    INDEX
    Explanations

    instances of the word "diagnosed" in the context of 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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    156
    +0.14
    0.8%
    148
    +0.14
    0.8%
    350
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.14
    0.01
    427
    +0.14
    0.01
    343
    +0.13
    0.01
    Negative Logits
    hores
    -1.81
    join
    -1.55
    igos
    -1.46
    ĥ½
    -1.46
    ¬
    -1.40
    )|^
    -1.39
    Īĺ
    -1.36
    izontal
    -1.33
    imi
    -1.31
    irds
    -1.30
    POSITIVE LOGITS
    ialog
    1.64
     emergencies
    1.54
     suspects
    1.53
    enough
    1.48
     remission
    1.48
     favour
    1.47
     enough
    1.42
    ovo
    1.39
     malignancy
    1.33
     yet
    1.33
    Activations Density 0.046%

    No Known Activations