© 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. 12350
    Prev
    Next
    INDEX
    Explanations

    phrases related to software licensing and conditions

    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
    466
    +0.11
    0.6%
    258
    +0.11
    0.6%
    78
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.11
    0.02
    34
    +0.11
    0.02
    107
    +0.10
    0.00
    Negative Logits
     battlefield
    -1.57
    kan
    -1.47
    iÄĩ
    -1.45
    oused
    -1.43
    ppen
    -1.42
    icz
    -1.36
    borg
    -1.32
    neys
    -1.30
     seats
    -1.28
    merce
    -1.28
    POSITIVE LOGITS
     disclaimer
    1.95
     WARRANTY
    1.88
     accompanying
    1.68
     COPYRIGHT
    1.67
     disclaim
    1.56
     limitations
    1.55
     notation
    1.51
     Redistributions
    1.46
    )](#
    1.45
     conclude
    1.43
    Activations Density 0.052%

    No Known Activations