© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28616
    Prev
    Next
    INDEX
    Explanations

    patterns of information related to numerical data or statistics

    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
    427
    +0.15
    0.8%
    487
    +0.14
    0.8%
    342
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    342
    +0.15
    0.04
    125
    +0.14
    0.04
    477
    +0.11
    0.06
    Negative Logits
    Ī
    -1.94
    [_
    -1.69
    ¹
    -1.59
    Ĩ
    -1.54
    §
    -1.54
    ľĵ
    -1.47
    ¨
    -1.45
    ®
    -1.41
    wordpress
    -1.41
      ↵
    -1.39
    POSITIVE LOGITS
     bars
    1.79
     depending
    1.69
    px
    1.62
     believed
    1.51
    nier
    1.51
    ite
    1.46
     respectively
    1.44
     grades
    1.43
    cents
    1.42
     evenly
    1.39
    Activations Density 0.303%

    No Known Activations