© 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. 11935
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to symptoms, conditions, and treatment outcomes

    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
    271
    +0.15
    0.9%
    418
    +0.12
    0.7%
    306
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.15
    0.03
    275
    +0.12
    0.02
    11
    +0.11
    0.03
    Negative Logits
     bait
    -1.49
     assembly
    -1.48
     Maker
    -1.48
     finder
    -1.46
     libraries
    -1.45
     ensemble
    -1.45
     cargo
    -1.45
     software
    -1.44
     Alexa
    -1.44
     crowds
    -1.42
    POSITIVE LOGITS
    ĻĤ
    4.98
    ij
    4.39
    ³
    4.33
    ŀ
    4.30
    ī
    4.25
    ĨĴ
    4.17
    Ń
    4.16
    ·
    4.11
    £
    4.08
    ¯
    4.05
    Activations Density 0.272%

    No Known Activations