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. 11748
    Prev
    Next
    INDEX
    Explanations

    expressions of repetition or ellipsis in 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
    +0.20
    1.1%
    127
    +0.15
    0.8%
    470
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.20
    0.03
    470
    +0.15
    0.03
    445
    +0.12
    0.01
    Negative Logits
    alties
    -1.84
    izations
    -1.77
    alty
    -1.76
    ties
    -1.73
    acters
    -1.72
    icity
    -1.71
     acquisition
    -1.66
    ificates
    -1.61
     development
    -1.61
    tees
    -1.60
    POSITIVE LOGITS
    ¸
    1.85
    unnumbered
    1.75
    не
    1.62
    Ŀ
    1.60
    Ķ
    1.56
     behold
    1.48
    quo
    1.44
    pite
    1.43
    denly
    1.41
    jest
    1.40
    Activations Density 0.085%

    No Known Activations