© 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. 11468
    Prev
    Next
    INDEX
    Explanations

    terms related to transactions or economic interactions

    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
    156
    +0.16
    0.9%
    153
    +0.14
    0.8%
    136
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.16
    0.05
    129
    +0.14
    0.01
    500
    +0.13
    0.04
    Negative Logits
    WORK
    -1.75
     guaranteed
    -1.72
    ELD
    -1.69
    Player
    -1.60
    UI
    -1.56
     Party
    -1.53
    SHIFT
    -1.52
    >>
    -1.49
    FIF
    -1.48
    !\
    -1.48
    POSITIVE LOGITS
    »¿
    2.78
    ¼
    2.71
    Ľ
    2.70
    ł
    2.67
    Ģ
    2.66
    Ļª
    2.60
    Ħ
    2.59
    ħ
    2.58
    Ĭ
    2.56
    2.55
    Activations Density 0.844%

    No Known Activations