© 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. 4-RES-SM
    11. 11845
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to navigation or movement through spaces

    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
    307
    +0.26
    1.5%
    466
    +0.14
    0.8%
    306
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.26
    0.05
    69
    +0.14
    0.04
    0
    +0.13
    0.03
    Negative Logits
    Ī
    -2.62
    Ĥ
    -2.46
    «
    -2.43
    ¿½
    -2.31
    ¨
    -2.31
    ·¸
    -2.30
    ¥
    -2.30
    Ģ
    -2.27
    ij
    -2.27
    ŀ
    -2.24
    POSITIVE LOGITS
     rigorous
    1.82
     successive
    1.78
     cracks
    1.74
     clenched
    1.64
    fitting
    1.64
     lengthy
    1.61
     sheer
    1.59
     infancy
    1.59
     customs
    1.58
     phases
    1.54
    Activations Density 0.292%

    No Known Activations