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. 29332
    Prev
    Next
    INDEX
    Explanations

    special characters or punctuation symbols in the text

    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%
    386
    +0.13
    0.7%
    165
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    165
    +0.15
    0.03
    192
    +0.13
    0.01
    386
    +0.12
    0.01
    Negative Logits
    ity
    -1.69
    itary
    -1.62
     carriers
    -1.58
    ellar
    -1.51
    inals
    -1.50
    ashi
    -1.50
    ames
    -1.48
     carrier
    -1.47
    ynam
    -1.43
    unes
    -1.41
    POSITIVE LOGITS
    IJ
    2.18
    kwargs
    2.03
    Īĺ
    2.00
    ĥ
    1.97
    ¢
    1.96
    ³
    1.81
    Ĩ
    1.81
    Competing
    1.77
    ½
    1.74
    Ķ
    1.71
    Activations Density 0.106%

    No Known Activations