© 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. 1-RES-SM
    11. 27757
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of capturing images or moments

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    +0.22
    1.3%
    148
    +0.18
    1.1%
    376
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.22
    0.02
    474
    +0.18
    0.02
    334
    +0.16
    0.02
    Negative Logits
    ĻĤ
    -2.19
    §
    -2.15
    "}](#
    -2.09
    Ī
    -2.04
    ĨĴ
    -1.97
    IJ
    -1.97
    ¹
    -1.96
    Į
    -1.92
    ĭ
    -1.87
    Ń
    -1.83
    POSITIVE LOGITS
     footage
    2.08
     sight
    2.08
     images
    1.87
     detail
    1.63
     scenes
    1.60
     image
    1.58
     clips
    1.57
     data
    1.55
     accuracy
    1.55
     information
    1.54
    Activations Density 0.090%

    No Known Activations