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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 12368
    Prev
    Next
    INDEX
    Explanations

    phrases related to numeric values and mathematical relationships

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    78
    +0.15
    0.8%
    478
    +0.13
    0.8%
    153
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    436
    +0.15
    0.02
    153
    +0.13
    0.02
    501
    +0.13
    0.01
    Negative Logits
    poons
    -1.53
    oscopy
    -1.51
    inating
    -1.50
    ialize
    -1.48
    ines
    -1.46
    ption
    -1.44
    arial
    -1.43
    ial
    -1.43
    inary
    -1.43
    ional
    -1.42
    POSITIVE LOGITS
    ĸ
    2.96
    Ĥ
    2.74
    Ĺ
    2.58
    Ľ
    2.56
    ¬
    2.56
    ĸ´
    2.54
    ¸
    2.53
    Ł
    2.52
    ĺ
    2.49
    ŀ
    2.48
    Activations Density 0.047%

    No Known Activations