© 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. 4-RES-SM
    11. 12239
    Prev
    Next
    INDEX
    Explanations

    references to the hepatitis B virus

    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
    78
    +0.18
    1.1%
    9
    +0.17
    1.1%
    156
    +0.15
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.18
    0.04
    425
    +0.17
    0.03
    162
    +0.15
    0.01
    Negative Logits
    ↵↵↵
    -4.79
              ↵
    -4.79
    ↵
    -4.79
    -4.79
    <|outofrange|>
    -4.79
    ↵
    -4.79
    ↵
    -4.79
    č↵
    -4.79
    ↵↵
    -4.79
    ↵↵
    -4.79
    POSITIVE LOGITS
     attacks
    1.45
    sworth
    1.36
     aboard
    1.33
    ettes
    1.31
     infection
    1.30
     ,"
    1.30
    ming
    1.27
     assays
    1.26
     Collaboration
    1.26
    ching
    1.25
    Activations Density 0.101%

    No Known Activations