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. 26861
    Prev
    Next
    INDEX
    Explanations

    time-related measurements and durations in experimental contexts

    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
    475
    +0.14
    0.7%
    12
    +0.12
    0.6%
    432
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.14
    0.05
    288
    +0.12
    0.05
    475
    +0.12
    0.05
    Negative Logits
     lords
    -1.70
    ½
    -1.64
     royalty
    -1.52
     steward
    -1.46
    ´
    -1.46
     spirit
    -1.44
    Ħ
    -1.43
     ducks
    -1.39
    ¦
    -1.39
     OW
    -1.37
    POSITIVE LOGITS
    umab
    2.05
    atinib
    1.80
    uncture
    1.79
    enden
    1.75
     compared
    1.70
    atal
    1.68
    ción
    1.67
     lasting
    1.65
     intervals
    1.65
    documentclass
    1.61
    Activations Density 0.295%

    No Known Activations