© 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. 27194
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "course" and its variations

    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
    478
    +0.14
    0.8%
    68
    +0.11
    0.6%
    415
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.34
    271
    +0.11
    0.13
    156
    +0.11
    0.17
    Negative Logits
    ®
    -2.56
    Ĵ
    -2.30
    IJ
    -2.28
    ŀ
    -2.21
    Ŀ
    -2.19
    ¿½
    -2.18
    ª
    -2.18
    ¿
    -2.10
    Ľ
    -2.06
    ħ
    -2.06
    POSITIVE LOGITS
     vagu
    1.65
     however
    1.50
     hearsay
    1.43
    printStackTrace
    1.41
     Ethical
    1.41
     Effect
    1.39
     silence
    1.39
     Opposition
    1.37
     nobody
    1.37
     meanwhile
    1.36
    Activations Density 1.193%

    No Known Activations