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. 29579
    Prev
    Next
    INDEX
    Explanations

    the word "as" used in various 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/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
    0.8%
    502
    +0.13
    0.8%
    340
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    502
    +0.15
    0.07
    340
    +0.13
    0.04
    123
    +0.13
    0.05
    Negative Logits
    sburg
    -1.57
    ctors
    -1.56
     excerpt
    -1.52
    s
    -1.51
    ptions
    -1.50
    NAME
    -1.50
    ered
    -1.45
    acks
    -1.42
     start
    -1.41
    aration
    -1.41
    POSITIVE LOGITS
    ylum
    2.10
    phalt
    1.95
    ĥ½
    1.80
     opposed
    1.79
    ymp
    1.62
    )',
    1.59
     well
    1.59
     belonging
    1.53
    ymmetric
    1.51
    leep
    1.50
    Activations Density 0.197%

    No Known Activations