© 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. 26132
    Prev
    Next
    INDEX
    Explanations

    terms related to telecommunications service providers

    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
    +0.22
    1.4%
    194
    +0.12
    0.7%
    131
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.22
    0.02
    174
    +0.12
    0.02
    156
    +0.12
    0.02
    Negative Logits
    woke
    -1.90
    urred
    -1.76
     fierce
    -1.71
     drastic
    -1.61
     profound
    -1.58
     countless
    -1.51
     heavenly
    -1.46
     relentless
    -1.44
     mighty
    -1.41
     tire
    -1.41
    POSITIVE LOGITS
    maid
    1.87
    ville
    1.81
    istics
    1.79
    inity
    1.77
    bags
    1.75
    ī
    1.75
    ics
    1.71
    port
    1.70
    Ģ
    1.68
    °
    1.68
    Activations Density 0.107%

    No Known Activations