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

    Neuronpedia

    Jacobian LensNEW
    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. 27835
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical or medical contexts

    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
    87
    +0.14
    0.8%
    84
    +0.13
    0.7%
    2
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.07
    271
    +0.13
    0.03
    156
    +0.13
    0.04
    Negative Logits
    Ģ
    -2.50
    Ķ
    -2.37
    Ĭ
    -2.29
    Į
    -2.20
    ŀ
    -2.19
    ®
    -2.19
    ĺ
    -2.19
    ¦
    -2.19
    ¸
    -2.18
    ¼
    -2.09
    POSITIVE LOGITS
    cles
    1.55
    iban
    1.46
     mob
    1.42
    clo
    1.41
    quee
    1.39
    bourg
    1.38
     ranged
    1.34
    lic
    1.34
     speaking
    1.32
    itat
    1.32
    Activations Density 0.170%

    No Known Activations