© 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. 26221
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to transitions in various contexts, particularly in personal and professional settings

    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
    +0.13
    0.7%
    30
    +0.12
    0.7%
    404
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.13
    0.01
    127
    +0.12
    0.02
    30
    +0.12
    0.01
    Negative Logits
    »¿
    -2.05
    ĸ´
    -2.01
    ½
    -2.00
    Ĥ¬
    -1.98
    ĥ½
    -1.97
    Ľ
    -1.88
    Ī
    -1.87
    į
    -1.87
    ¤
    -1.87
    ©
    -1.83
    POSITIVE LOGITS
     occurs
    1.88
     dipole
    1.61
     period
    1.52
     phase
    1.51
     underway
    1.50
     between
    1.49
     occurred
    1.48
    ais
    1.48
     stage
    1.45
     involves
    1.45
    Activations Density 0.177%

    No Known Activations