© 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 EvalsExportsinterp-engineNEWAPI 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. 24637
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences that emphasize a sense of connection or movement, particularly in relation to rising or increasing dynamics

    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
    478
    +0.13
    0.7%
    69
    +0.13
    0.7%
    127
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.13
    -0.01
    478
    +0.13
    0.01
    69
    +0.12
    0.07
    Negative Logits
    arium
    -1.90
    Ī
    -1.79
    Īĺ
    -1.69
    sters
    -1.64
    entially
    -1.63
    istry
    -1.57
    ually
    -1.56
    ī
    -1.55
    ŀ
    -1.54
    encia
    -1.53
    POSITIVE LOGITS
    rian
    1.75
    down
    1.54
     ridiculous
    1.47
     slower
    1.41
    DLL
    1.41
     lanes
    1.40
    hores
    1.39
     QT
    1.38
     tad
    1.38
     faster
    1.38
    Activations Density 1.228%

    No Known Activations