© 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. 2-RES-SM
    11. 29992
    Prev
    Next
    INDEX
    Explanations

    terms related to hepatitis and liver 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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    +0.15
    0.9%
    111
    +0.14
    0.8%
    321
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.15
    0.02
    254
    +0.14
    0.01
    481
    +0.12
    0.01
    Negative Logits
    ĺ
    -2.25
    IJ
    -2.21
    ŀ
    -2.18
    Ŀ
    -2.12
    ł
    -2.06
    ĻĤ
    -2.04
    ´
    -2.00
    ±
    -1.94
    ¤
    -1.94
    °
    -1.79
    POSITIVE LOGITS
     pylori
    2.06
    avirus
    2.03
    abad
    1.81
     infected
    1.76
     infection
    1.75
    ogenicity
    1.74
     aftermath
    1.70
     epidemic
    1.69
    istan
    1.67
     damage
    1.64
    Activations Density 0.118%

    No Known Activations