© 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. 4-RES-SM
    11. 14445
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions of continuation or persistence

    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
    327
    +0.15
    0.8%
    364
    +0.14
    0.8%
    404
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    327
    +0.15
    0.04
    364
    +0.14
    0.04
    404
    +0.12
    0.02
    Negative Logits
    ĺ
    -4.87
    ĥ½
    -4.70
    ľĵ
    -4.51
    ij
    -4.50
    ¾
    -4.49
    Ĩ
    -4.47
    »¿
    -4.46
    -4.44
         ↵
    -4.44
    č↵č↵
    -4.44
    POSITIVE LOGITS
     onward
    1.98
     to
    1.91
     throughout
    1.77
     unchanged
    1.77
     untreated
    1.77
     existence
    1.71
     onwards
    1.67
     thereafter
    1.61
     Reading
    1.60
    emente
    1.57
    Activations Density 0.350%

    No Known Activations