© 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. 13041
    Prev
    Next
    INDEX
    Explanations

    expressions related to motivation and inspiration

    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
    510
    +0.19
    1.1%
    307
    +0.16
    0.9%
    38
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.19
    0.07
    38
    +0.16
    0.09
    176
    +0.12
    0.09
    Negative Logits
    Īĺ
    -4.81
    ©
    -4.80
    ij
    -4.61
    ĻĤ
    -4.59
    £
    -4.49
            ↵
    -4.27
    -4.27
    ↵
    -4.27
     ↵
    -4.27
    -4.27
    POSITIVE LOGITS
     us
    2.49
    ingly
    2.46
     shoppers
    2.34
     guests
    2.31
     ourselves
    2.30
     him
    2.29
    ously
    2.29
     others
    2.28
     audiences
    2.24
     visitors
    2.22
    Activations Density 1.322%

    No Known Activations