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. 29276
    Prev
    Next
    INDEX
    Explanations

    references to recent events or studies

    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
    308
    +0.11
    0.6%
    11
    +0.11
    0.6%
    142
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    308
    +0.11
    0.02
    246
    +0.11
    0.02
    418
    +0.10
    0.00
    Negative Logits
     immediately
    -1.58
    oso
    -1.52
     await
    -1.51
     evenly
    -1.51
     accordingly
    -1.51
     withstand
    -1.50
     surround
    -1.48
    IJ
    -1.46
     utmost
    -1.45
     trust
    -1.44
    POSITIVE LOGITS
     generations
    1.79
    oral
    1.68
     past
    1.66
    itations
    1.64
     decades
    1.63
     publication
    1.62
     occasions
    1.62
    citations
    1.61
     additions
    1.58
     comments
    1.52
    Activations Density 0.057%

    No Known Activations