Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 11802
    Prev
    Next
    INDEX
    Explanations

    conjunctions and their usage in connecting phrases or clauses

    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
    478
    +0.15
    0.9%
    494
    +0.14
    0.8%
    332
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.15
    0.06
    209
    +0.14
    0.07
    332
    +0.14
    0.05
    Negative Logits
    !”
    -2.06
    ģ
    -1.79
    £
    -1.74
    java
    -1.73
     {#
    -1.70
     offence
    -1.70
    .“
    -1.68
     ðŁĻĤ
    -1.68
    ²
    -1.68
    !
    -1.66
    POSITIVE LOGITS
     its
    1.80
     oligonucle
    1.75
    rogens
    1.74
     consequent
    1.68
    hift
    1.67
     hence
    1.61
     average
    1.52
     consequently
    1.52
     subsequent
    1.50
     then
    1.49
    Activations Density 0.511%

    No Known Activations