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. 26789
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to research studies and hypotheses

    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
    23
    +0.22
    1.3%
    198
    +0.14
    0.8%
    478
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.22
    0.08
    442
    +0.14
    0.07
    198
    +0.14
    0.03
    Negative Logits
     –
    -1.68
    boards
    -1.61
     (.
    -1.60
     Fans
    -1.54
    pace
    -1.50
    Category
    -1.49
     Photography
    -1.48
    arm
    -1.47
    '):
    -1.47
    %"
    -1.46
    POSITIVE LOGITS
     0000000000000000000000000000000000
    1.64
     promise
    1.60
     rescue
    1.59
     yours
    1.56
     grateful
    1.52
     highlight
    1.50
     mine
    1.50
     investigating
    1.47
     motivated
    1.44
     futile
    1.44
    Activations Density 0.862%

    No Known Activations