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. 11616
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "distributed" in the context of software licensing

    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
    74
    +0.12
    0.7%
    254
    +0.12
    0.7%
    73
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.12
    0.02
    74
    +0.12
    0.02
    359
    +0.11
    0.02
    Negative Logits
    ĥ½
    -2.18
    ypse
    -2.04
    ľĵ
    -2.02
    Īĺ
    -1.81
    ouses
    -1.78
    »¿
    -1.77
    ses
    -1.72
    ĭ
    -1.68
    plasia
    -1.65
    tis
    -1.62
    POSITIVE LOGITS
     counsel
    1.58
     degrees
    1.51
     denial
    1.49
     licenses
    1.46
     xe
    1.41
     adj
    1.40
     sli
    1.31
     waiver
    1.31
     slack
    1.29
     nonsense
    1.26
    Activations Density 0.041%

    No Known Activations