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. 1-RES-SM
    6. 26776
    Prev
    Next
    INDEX
    Explanations

    dates, specifically in the format of month and day

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    59
    +0.15
    0.8%
    369
    +0.14
    0.8%
    281
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.15
    0.02
    410
    +0.14
    0.02
    281
    +0.14
    0.02
    Negative Logits
     least
    -1.62
    bbe
    -1.60
    eer
    -1.51
     typical
    -1.34
    atically
    -1.32
     transmission
    -1.32
     pupp
    -1.31
     hypothetical
    -1.30
     demons
    -1.29
    abouts
    -1.29
    POSITIVE LOGITS
    itor
    1.81
    eno
    1.79
    iors
    1.78
    aration
    1.77
    itin
    1.75
    arez
    1.73
    iani
    1.71
    iets
    1.70
    ney
    1.63
    mented
    1.63
    Activations Density 0.054%

    No Known Activations