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. 11425
    Prev
    Next
    INDEX
    Explanations

    references to Ireland and Irish identity

    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
    156
    +0.20
    1.2%
    410
    +0.18
    1.0%
    397
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.20
    0.04
    279
    +0.18
    0.03
    1
    +0.15
    0.02
    Negative Logits
    ages
    -1.80
    aneously
    -1.60
    uras
    -1.58
    age
    -1.51
    aneous
    -1.51
    itively
    -1.47
     nothing
    -1.47
    ays
    -1.41
     effect
    -1.40
    ı
    -1.35
    POSITIVE LOGITS
    bane
    2.10
    wald
    1.81
    berg
    1.76
    bolt
    1.73
    gow
    1.72
    bour
    1.72
    vill
    1.68
    ium
    1.62
    bourg
    1.61
    mac
    1.59
    Activations Density 0.175%

    No Known Activations