© 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. 28243
    Prev
    Next
    INDEX
    Explanations

    variations of words related to nationality and cultural references

    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
    168
    +0.13
    0.7%
    254
    +0.13
    0.7%
    223
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.13
    0.02
    168
    +0.13
    0.02
    254
    +0.12
    0.02
    Negative Logits
    pone
    -1.92
    pecific
    -1.71
    pcbi
    -1.67
    areness
    -1.62
    APTER
    -1.61
    igation
    -1.59
    itiveness
    -1.57
    oretical
    -1.56
    pgen
    -1.55
    cknow
    -1.54
    POSITIVE LOGITS
    ¿½
    2.00
    IJ
    1.94
    °
    1.89
    ª
    1.86
    ĨĴ
    1.81
    Ń
    1.78
    ĵ
    1.78
    ĥ
    1.76
    Į
    1.73
    ·
    1.72
    Activations Density 0.142%

    No Known Activations