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

    Neuronpedia

    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. 2-RES-SM
    11. 30002
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and temporal markers

    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
    71
    +0.12
    0.7%
    476
    +0.12
    0.7%
    358
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.12
    0.01
    358
    +0.12
    0.02
    211
    +0.12
    0.02
    Negative Logits
    Ŀ
    -3.66
    Ĺ
    -3.42
    ĵ
    -3.38
    Ľ
    -3.37
    ³
    -3.36
    Ĩ
    -3.33
    Ļª
    -3.29
    ĭ
    -3.25
    İ
    -3.24
    ¶
    -3.23
    POSITIVE LOGITS
    ças
    1.89
    imetry
    1.83
    uality
    1.82
    sworth
    1.69
    irectional
    1.67
    picker
    1.61
    plit
    1.59
    backs
    1.56
    astic
    1.55
    igraphy
    1.51
    Activations Density 0.090%

    No Known Activations