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. 29442
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to the Arabic language or culture

    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
    2
    +0.15
    0.9%
    164
    +0.11
    0.6%
    136
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.15
    0.03
    18
    +0.11
    0.03
    417
    +0.11
    0.03
    Negative Logits
    CDATA
    -1.58
    blogger
    -1.53
    LED
    -1.50
    plit
    -1.49
    Argued
    -1.41
    unreadable
    -1.38
    built
    -1.38
     metab
    -1.38
     ignition
    -1.37
    xymatrix
    -1.36
    POSITIVE LOGITS
    ytics
    2.04
    veolar
    2.00
    ·
    1.87
    oupe
    1.84
    º
    1.84
    ī
    1.83
    ucci
    1.81
    cohol
    1.80
     Pradesh
    1.76
    ogue
    1.73
    Activations Density 0.187%

    No Known Activations